Hua Wu


2024

pdf
Autoregressive Pre-Training on Pixels and Texts
Yekun Chai | Qingyi Liu | Jingwu Xiao | Shuohuan Wang | Yu Sun | Hua Wu
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

The integration of visual and textual information represents a promising direction in the advancement of language models. In this paper, we explore the dual modality of language—both visual and textual—within an autoregressive framework, pre-trained on both document images and texts. Our method employs a multimodal training strategy, utilizing visual data through next patch prediction with a regression head and/or textual data through next token prediction with a classification head. We focus on understanding the interaction between these two modalities and their combined impact on model performance. Our extensive evaluation across a wide range of benchmarks shows that incorporating both visual and textual data significantly improves the performance of pixel-based language models. Remarkably, we find that a unidirectional pixel-based model trained solely on visual data can achieve comparable results to state-of-the-art bidirectional models on several language understanding tasks. This work uncovers the untapped potential of integrating visual and textual modalities for more effective language modeling. We release our code, data, and model checkpoints at https://github.com/ernie-research/pixelgpt.

pdf
On Training Data Influence of GPT Models
Yekun Chai | Qingyi Liu | Shuohuan Wang | Yu Sun | Qiwei Peng | Hua Wu
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Amidst the rapid advancements in generative language models, the investigation of how training data shapes the performance of GPT models is still emerging. This paper presents GPTfluence, a novel approach that leverages a featurized simulation to assess the impact of training examples on the training dynamics of GPT models. Our approach not only traces the influence of individual training instances on performance trajectories, such as loss and other key metrics, on targeted test points but also enables a comprehensive comparison with existing methods across various training scenarios in GPT models, ranging from 14 million to 2.8 billion parameters, across a range of downstream tasks. Contrary to earlier methods that struggle with generalization to new data, GPTfluence introduces a parameterized simulation of training dynamics, demonstrating robust generalization capabilities to unseen training data. This adaptability is evident across both fine-tuning and instruction-tuning scenarios, spanning tasks in natural language understanding and generation. We make our code and data publicly available at https://github.com/ernie-research/gptfluence.

pdf
BASES: Large-scale Web Search User Simulation with Large Language Model based Agents
Ruiyang Ren | Peng Qiu | Yingqi Qu | Jing Liu | Xin Zhao | Hua Wu | Ji-Rong Wen | Haifeng Wang
Findings of the Association for Computational Linguistics: EMNLP 2024

Due to the excellent capacities of large language models (LLMs), it becomes feasible to develop LLM-based agents for reliable user simulation. Considering the scarcity and limit (e.g., privacy issues) of real user data, in this paper, we conduct large-scale user simulations for the web search scenario to improve the analysis and modeling of user search behavior. Specially, we propose BASES, a novel user simulation framework with LLM-based agents, designed to facilitate comprehensive simulations of web search user behaviors. Our simulation framework can generate unique user profiles at scale, which subsequently leads to diverse search behaviors. To demonstrate the effectiveness of BASES, we conduct evaluation experiments based on two human benchmarks in both Chinese and English, demonstrating that BASES can effectively simulate large-scale human-like search behaviors. To further accommodate the research on web search, we develop WARRIORS, a new large-scale dataset encompassing web search user behaviors, including both Chinese and English versions, which can greatly bolster research in the field of information retrieval.

pdf
An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation
Pengzhi Gao | Ruiqing Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neural machine translation (NMT) field. Can we also boost end-to-end (E2E) speech-to-text translation (ST) by leveraging consistency regularization? In this paper, we conduct empirical studies on intra-modal and cross-modal consistency and propose two training strategies, SimRegCR and SimZeroCR, for E2E ST in regular and zero-shot scenarios. Experiments on the MuST-C benchmark show that our approaches achieve state-of-the-art (SOTA) performance in most translation directions. The analyses prove that regularization brought by the intra-modal consistency, instead of the modality gap, is crucial for the regular E2E ST, and the cross-modal consistency could close the modality gap and boost the zero-shot E2E ST performance.

pdf
NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time
Yilong Chen | Guoxia Wang | Junyuan Shang | Shiyao Cui | Zhenyu Zhang | Tingwen Liu | Shuohuan Wang | Yu Sun | Dianhai Yu | Hua Wu
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the extensive memory consumption of KV Cache involving long-context modeling. Despite several works proposing to evict unnecessary tokens from the KV Cache, most of them rely on the biased local statistics of accumulated attention scores and report performance using unconvincing metric like perplexity on inadequate short-text evaluation. In this paper, we propose NACL, a general framework for long-context KV cache eviction that achieves more optimal and efficient eviction in a single operation during the encoding phase. Due to NACL’s efficiency, we combine more accurate attention score statistics in Proxy-Tokens Eviction with the diversified random eviction strategy of Random Eviction, aiming to alleviate the issue of attention bias and enhance the robustness in maintaining pivotal tokens for long-context modeling tasks. Notably, our method significantly improves the performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to with over 95% performance maintenance. Code available at https://github.com/PaddlePaddle/Research/tree/master/NLP/ACL2024-NACL.

pdf
LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion
Yilong Chen | Junyuan Shang | Zhenyu Zhang | Shiyao Cui | Tingwen Liu | Shuohuan Wang | Yu Sun | Hua Wu
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In the new era of language models, small models (with billions of parameter sizes) are receiving increasing attention due to their flexibility and cost-effectiveness in deployment. However, limited by the model size, the performance of small models trained from scratch may often be unsatisfactory. Learning a stronger and smaller model with the help of larger models is an intuitive idea. Inspired by the observing modular structures in preliminary analysis, we propose LEMON to learn competent initial points for smaller models by fusing parameters from larger models, thereby laying a solid foundation for subsequent training. Specifically, the parameter fusion process involves two operators for layer and dimension, respectively, and we also introduce controllable receptive fields to model the prior parameter characteristics. In this way, the larger model could be transformed into any specific smaller scale and architecture. Starting from LLaMA 2-7B, we revive two stronger and smaller models with 1.3B and 2.7B. Experimental results demonstrate that the fusion-based method exhibits flexibility and outperforms a series of competitive baselines in terms of both effectiveness and efficiency.

pdf
QDMR-based Planning-and-Solving Prompting for Complex Reasoning Tasks
Jinfeng Huang | Qiaoqiao She | Wenbin Jiang | Hua Wu | Yang Hao | Tong Xu | Feng Wu
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Chain-of-Thought prompting has improved reasoning capability of large language models (LLM). However, it still is challenging to guarantee the effectiveness and stability for questions requiring complicated reasoning. Recently, Plan-and-Solve prompting enhances the reasoning capability for complex questions by planning the solution steps firstly and then solving them step by step, but it suffers the difficulty to represent and execute the problem-solving logic of complex questions. To deal with these challenges, in this work, we propose a novel Plan-and-Solve prompting method based on Question Decomposition Meaning Representation (QDMR). Specifically, this method first allows the LLM to generate a QDMR graph to represent the problem-solving logic, which is a directed acyclic graph composed of sub-questions. Then, the LLM generates a specific solving process based on the QDMR graph. When solving each sub-question, it can locate the preceding sub-questions and their answers according to the QDMR graph, and then utilize this information for solution. Compared with existing Plan-and-Solve prompting techniques, our method can not only represent the problem-solving logic of complicated questions more accurately with the aid of QDMR graph, but also deliver the dependence information accurately for different solution steps according to the QDMR graph. In addition, with the supervised fine-tuning on the Allen Institute dataset, the decomposing capability of LLM for complicated questions can be considerably enhanced. Extensive experiments show that our method has achieve a great significance in arithmetic reasoning and commonsense reasoning task by comparing the classical Chain-of-Thought prompting and Plan-and-Solve prompting techniques, and the improvements achieved are even greater for problems with more reasoning steps.

2023

pdf
Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling
Mingzhu Cai | Siqi Bao | Xin Tian | Huang He | Fan Wang | Hua Wu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv. There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator. QKConv is optimized through joint training, which produces the response by exploring multiple candidate queries and leveraging corresponding selected knowledge. The joint training solely relies on the dialogue context and target response, getting exempt from extra query annotations or knowledge provenances. To evaluate the effectiveness of the proposed QKConv, we conduct experiments on three representative knowledge-intensive conversation datasets: conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation. Experimental results reveal that QKConv performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.

pdf
Towards Boosting the Open-Domain Chatbot with Human Feedback
Hua Lu | Siqi Bao | Huang He | Fan Wang | Hua Wu | Haifeng Wang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses. This phenomenon might mainly result from the deficiency of annotated human-human conversations and the misalignment with human preference. In this paper, we propose a novel and efficient framework Diamante to boost the open-domain chatbot, where two kinds of human feedback (including explicit demonstration and implicit preference) are collected and leveraged. By asking annotators to select or amend the model-generated candidate responses, Diamante efficiently collects the human demonstrated responses and constructs a Chinese chit-chat dataset. To enhance the alignment with human preference, Diamante leverages the implicit preference in the data collection process and introduces the generation-evaluation joint training. Comprehensive experiments indicate that the Diamante dataset and joint training paradigm can significantly boost the performance of pre-trained dialogue models. The overall engagingness of the previous state-of-the-art model has been improved remarkably by 50% in Chinese open-domain conversations.

pdf
TOME: A Two-stage Approach for Model-based Retrieval
Ruiyang Ren | Wayne Xin Zhao | Jing Liu | Hua Wu | Ji-Rong Wen | Haifeng Wang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recently, model-based retrieval has emerged as a new paradigm in text retrieval that discards the index in the traditional retrieval model and instead memorizes the candidate corpora using model parameters. This design employs a sequence-to-sequence paradigm to generate document identifiers, which enables the complete capture of the relevance between queries and documents and simplifies the classic index-retrieval-rerank pipeline. Despite its attractive qualities, there remain several major challenges in model-based retrieval, including the discrepancy between pre-training and fine-tuning, and the discrepancy between training and inference. To deal with the above challenges, we propose a novel two-stage model-based retrieval approach called TOME, which makes two major technical contributions, including the utilization of tokenized URLs as identifiers and the design of a two-stage generation architecture. We also propose a number of training strategies to deal with the training difficulty as the corpus size increases. Extensive experiments and analysis on MS MARCO and Natural Questions demonstrate the effectiveness of our proposed approach, and we investigate the scaling laws of TOME by examining various influencing factors.

pdf
Learning In-context Learning for Named Entity Recognition
Jiawei Chen | Yaojie Lu | Hongyu Lin | Jie Lou | Wei Jia | Dai Dai | Hua Wu | Boxi Cao | Xianpei Han | Le Sun
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function Lambda_instruction, demonstrations, text.M, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., (Lambda . M) (instruction, demonstrations) ->F where F will be a new entity extractor F: text -> entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.

pdf
Towards Zero-Shot Persona Dialogue Generation with In-Context Learning
Xinchao Xu | Zeyang Lei | Wenquan Wu | Zheng-Yu Niu | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: ACL 2023

Much work has been done to improve persona consistency by finetuning a pretrained dialogue model on high-quality human-annoated persona datasets. However, these methods still face the challenges of high cost and poor scalability. To this end, we propose a simple-yet-effective approach to significantly improve zero-shot persona consistency via in-context learning. Specifically, we first pre-train a persona-augmented dialogue generation model and then utilize in-context prompting mechanism to realize zero-shot persona customization. Experimental results demonstrate that our method can dramatically improve persona consistency without compromising coherence and informativeness in zero-shot settings.

pdf
ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
Yekun Chai | Shuohuan Wang | Chao Pang | Yu Sun | Hao Tian | Hua Wu
Findings of the Association for Computational Linguistics: ACL 2023

Software engineers working with the same programming language (PL) may speak different natural languages (NLs) and vice versa, erecting huge barriers to communication and working efficiency. Recent studies have demonstrated the effectiveness of generative pre-training in computer programs, yet they are always English-centric. In this work, we step towards bridging the gap between multilingual NLs and multilingual PLs for large language models (LLMs). We release ERNIE-Code, a unified pre-trained language model for 116 NLs and 6 PLs. We employ two methods for universal cross-lingual pre-training: span-corruption language modeling that learns patterns from monolingual NL or PL; and pivot-based translation language modeling that relies on parallel data of many NLs and PLs. Extensive results show that ERNIE-Code outperforms previous multilingual LLMs for PL or NL across a wide range of end tasks of code intelligence, including multilingual code-to-text, text-to-code, code-to-code, and text-to-text generation. We further show its advantage of zero-shot prompting on multilingual code summarization and text-to-text translation. We release our code and pre-trained checkpoints.

pdf
Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
Pengzhi Gao | Liwen Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: ACL 2023

The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised directions to zero-shot directions, the multilingual NMT model is expected to learn universal representations across different languages. This paper introduces a cross-lingual consistency regularization, CrossConST, to bridge the representation gap among different languages and boost zero-shot translation performance. The theoretical analysis shows that CrossConST implicitly maximizes the probability distribution for zero-shot translation, and the experimental results on both low-resource and high-resource benchmarks show that CrossConST consistently improves the translation performance. The experimental analysis also proves that CrossConST could close the sentence representation gap and better align the representation space. Given the universality and simplicity of CrossConST, we believe it can serve as a strong baseline for future multilingual NMT research.

pdf
IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding
Peijian Gu | Yaozong Shen | Lijie Wang | Quan Wang | Hua Wu | Zhendong Mao
Findings of the Association for Computational Linguistics: EMNLP 2023

Instance attribution (IA) aims to identify the training instances leading to the prediction of a test example, helping researchers understand the dataset better and optimize data processing. While many IA methods have been proposed recently, how to evaluate them still remains open. Previous evaluations of IA only focus on one or two dimensions and are not comprehensive. In this work, we introduce IAEval for IA methods, a systematic and comprehensive evaluation scheme covering four significant requirements: sufficiency, completeness, stability and plausibility. We elaborately design novel metrics to measure these requirements for the first time. Three representative IA methods are evaluated under IAEval on four natural language understanding datasets. Extensive experiments confirmed the effectiveness of IAEval and exhibited its ability to provide comprehensive comparison among IA methods. With IAEval, researchers can choose the most suitable IA methods for applications like model debugging.

pdf
A Thorough Examination on Zero-shot Dense Retrieval
Ruiyang Ren | Yingqi Qu | Jing Liu | Xin Zhao | Qifei Wu | Yuchen Ding | Hua Wu | Haifeng Wang | Ji-Rong Wen
Findings of the Association for Computational Linguistics: EMNLP 2023

Recent years have witnessed the significant advance in dense retrieval (DR) based on powerful pre-trained language models (PLM). DR models have achieved excellent performance in several benchmark datasets, while they are shown to be not as competitive as traditional sparse retrieval models (e.g., BM25) in a zero-shot retrieval setting. However, in the related literature, there still lacks a detailed and comprehensive study on zero-shot retrieval. In this paper, we present the first thorough examination of the zero-shot capability of DR models. We aim to identify the key factors and analyze how they affect zero-shot retrieval performance. In particular, we discuss the effect of several key factors related to source training set, analyze the potential bias from the target dataset, and review and compare existing zero-shot DR models. Our findings provide important evidence to better understand and develop zero-shot DR models.

pdf
IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models
Xiaoyue Wang | Xin Liu | Lijie Wang | Yaoxiang Wang | Jinsong Su | Hua Wu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

As commonly-used methods for debiasing natural language understanding (NLU) models, dataset refinement approaches heavily rely on manual data analysis, and thus maybe unable to cover all the potential biased features. In this paper, we propose IBADR, an Iterative Bias-Aware Dataset Refinement framework, which debiases NLU models without predefining biased features. We maintain an iteratively expanded sample pool. Specifically, at each iteration, we first train a shallow model to quantify the bias degree of samples in the pool. Then, we pair each sample with a bias indicator representing its bias degree, and use these extended samples to train a sample generator. In this way, this generator can effectively learn the correspondence relationship between bias indicators and samples. Furthermore, we employ the generator to produce pseudo samples with fewer biased features by feeding specific bias indicators. Finally, we incorporate the generated pseudo samples into the pool. Experimental results and in-depth analyses on two NLU tasks show that IBADR not only significantly outperforms existing dataset refinement approaches, achieving SOTA, but also is compatible with model-centric methods.

pdf
Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization
Pengzhi Gao | Liwen Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track

Multilingual sentence representations are the foundation for similarity-based bitext mining, which is crucial for scaling multilingual neural machine translation (NMT) system to more languages. In this paper, we introduce MuSR: a one-for-all Multilingual Sentence Representation model that supports 223 languages. Leveraging billions of English-centric parallel corpora, we train a multilingual Transformer encoder, coupled with an auxiliary Transformer decoder, by adopting a multilingual NMT framework with CrossConST, a cross-lingual consistency regularization technique proposed in Gao et al. (2023). Experimental results on multilingual similarity search and bitext mining tasks show the effectiveness of our approach. Specifically, MuSR achieves superior performance over LASER3 (Heffernan et al., 2022) which consists of 148 independent multilingual sentence encoders.

pdf
ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models
Pengfei Zhu | Chao Pang | Yekun Chai | Lei Li | Shuohuan Wang | Yu Sun | Hao Tian | Hua Wu
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations

2022

pdf
A Fine-grained Interpretability Evaluation Benchmark for Neural NLP
Lijie Wang | Yaozong Shen | Shuyuan Peng | Shuai Zhang | Xinyan Xiao | Hao Liu | Hongxuan Tang | Ying Chen | Hua Wu | Haifeng Wang
Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability on different types of tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark (https://www.luge.ai/#/luge/task/taskDetail?taskId=15) and hope it can facilitate the research in building trustworthy systems.

pdf
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Pengzhi Gao | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and unidirectional finetuning. Both procedures utilize SimCut, a simple regularization method that forces the consistency between the output distributions of the original and the cutoff sentence pairs. Without leveraging extra dataset via back-translation or integrating large-scale pretrained model, Bi-SimCut achieves strong translation performance across five translation benchmarks (data sizes range from 160K to 20.2M): BLEU scores of 31.16 for ende and 38.37 for deen on the IWSLT14 dataset, 30.78 for ende and 35.15 for deen on the WMT14 dataset, and 27.17 for zhen on the WMT17 dataset. SimCut is not a new method, but a version of Cutoff (Shen et al., 2020) simplified and adapted for NMT, and it could be considered as a perturbation-based method. Given the universality and simplicity of Bi-SimCut and SimCut, we believe they can serve as strong baselines for future NMT research.

pdf
Non-Autoregressive Chinese ASR Error Correction with Phonological Training
Zheng Fang | Ruiqing Zhang | Zhongjun He | Hua Wu | Yanan Cao
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Automatic Speech Recognition (ASR) is an efficient and widely used input method that transcribes speech signals into text. As the errors introduced by ASR systems will impair the performance of downstream tasks, we introduce a post-processing error correction method, PhVEC, to correct errors in text space. For the errors in ASR result, existing works mainly focus on fixed-length corrections, modifying each wrong token to a correct one (one-to-one correction), but rarely consider the variable-length correction (one-to-many or many-to-one correction). In this paper, we propose an efficient non-autoregressive (NAR) method for Chinese ASR error correction for both cases. Instead of conventionally predicting the sentence length in NAR methods, we propose a novel approach that uses phonological tokens to extend the source sentence for variable-length correction, enabling our model to generate phonetically similar corrections. Experimental results on datasets of different domains show that our method achieves significant improvement in word error rate reduction and speeds up the inference by 6.2 times compared with the autoregressive model.

pdf bib
Findings of the Third Workshop on Automatic Simultaneous Translation
Ruiqing Zhang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Haifeng Wang | Liang Huang | Qun Liu | Julia Ive | Wolfgang Macherey
Proceedings of the Third Workshop on Automatic Simultaneous Translation

This paper reports the results of the shared task we hosted on the Third Workshop of Automatic Simultaneous Translation (AutoSimTrans). The shared task aims to promote the development of text-to-text and speech-to-text simultaneous translation, and includes Chinese-English and English-Spanish tracks. The number of systems submitted this year has increased fourfold compared with last year. Additionally, the top 1 ranked system in the speech-to-text track is the first end-to-end submission we have received in the past three years, which has shown great potential. This paper reports the results and descriptions of the 14 participating teams, compares different evaluation metrics, and revisits the ranking method.

pdf
Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals
Zeming Liu | Jun Xu | Zeyang Lei | Haifeng Wang | Zheng-Yu Niu | Hua Wu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most dialog systems posit that users have figured out clear and specific goals before starting an interaction. For example, users have determined the departure, the destination, and the travel time for booking a flight. However, in many scenarios, limited by experience and knowledge, users may know what they need, but still struggle to figure out clear and specific goals by determining all the necessary slots. In this paper, we identify this challenge, and make a step forward by collecting a new human-to-human mixed-type dialog corpus. It contains 5k dialog sessions and 168k utterances for 4 dialog types and 5 domains. Within each session, an agent first provides user-goal-related knowledge to help figure out clear and specific goals, and then help achieve them. Furthermore, we propose a mixed-type dialog model with a novel Prompt-based continual learning mechanism. Specifically, the mechanism enables the model to continually strengthen its ability on any specific type by utilizing existing dialog corpora effectively.

pdf
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation
Zhe Hu | Hou Pong Chan | Jiachen Liu | Xinyan Xiao | Hua Wu | Lifu Huang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that require proper content control and planning to form a coherent high-level logical flow. In this work, we propose PLANET, a novel generation framework leveraging autoregressive self-attention mechanism to conduct content planning and surface realization dynamically. To guide the generation of output sentences, our framework enriches the Transformer decoder with latent representations to maintain sentence-level semantic plans grounded by bag-of-words. Moreover, we introduce a new coherence-based contrastive learning objective to further improve the coherence of output. Extensive experiments are conducted on two challenging long-form text generation tasks including counterargument generation and opinion article generation. Both automatic and human evaluations show that our method significantly outperforms strong baselines and generates more coherent texts with richer contents.

pdf
Unified Structure Generation for Universal Information Extraction
Yaojie Lu | Qing Liu | Dai Dai | Xinyan Xiao | Hongyu Lin | Xianpei Han | Le Sun | Hua Wu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. In this paper, we propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources. Specifically, UIE uniformly encodes different extraction structures via a structured extraction language, adaptively generates target extractions via a schema-based prompt mechanism – structural schema instructor, and captures the common IE abilities via a large-scale pretrained text-to-structure model. Experiments show that UIE achieved the state-of-the-art performance on 4 IE tasks, 13 datasets, and on all supervised, low-resource, and few-shot settings for a wide range of entity, relation, event and sentiment extraction tasks and their unification. These results verified the effectiveness, universality, and transferability of UIE.

pdf
Learning Adaptive Segmentation Policy for End-to-End Simultaneous Translation
Ruiqing Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

End-to-end simultaneous speech-to-text translation aims to directly perform translation from streaming source speech to target text with high translation quality and low latency. A typical simultaneous translation (ST) system consists of a speech translation model and a policy module, which determines when to wait and when to translate. Thus the policy is crucial to balance translation quality and latency. Conventional methods usually adopt fixed policies, e.g. segmenting the source speech with a fixed length and generating translation. However, this method ignores contextual information and suffers from low translation quality. This paper proposes an adaptive segmentation policy for end-to-end ST. Inspired by human interpreters, the policy learns to segment the source streaming speech into meaningful units by considering both acoustic features and translation history, maintaining consistency between the segmentation and translation. Experimental results on English-German and Chinese-English show that our method achieves a good accuracy-latency trade-off over recently proposed state-of-the-art methods.

pdf bib
CDConv: A Benchmark for Contradiction Detection in Chinese Conversations
Chujie Zheng | Jinfeng Zhou | Yinhe Zheng | Libiao Peng | Zhen Guo | Wenquan Wu | Zheng-Yu Niu | Hua Wu | Minlie Huang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Dialogue contradiction is a critical issue in open-domain dialogue systems. The contextualization nature of conversations makes dialogue contradiction detection rather challenging. In this work, we propose a benchmark for Contradiction Detection in Chinese Conversations, namely CDConv. It contains 12K multi-turn conversations annotated with three typical contradiction categories: Intra-sentence Contradiction, Role Confusion, and History Contradiction. To efficiently construct the CDConv conversations, we devise a series of methods for automatic conversation generation, which simulate common user behaviors that trigger chatbots to make contradictions. We conduct careful manual quality screening of the constructed conversations and show that state-of-the-art Chinese chatbots can be easily goaded into making contradictions. Experiments on CDConv show that properly modeling contextual information is critical for dialogue contradiction detection, but there are still unresolved challenges that require future research.

pdf
DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine
Yifu Qiu | Hongyu Li | Yingqi Qu | Ying Chen | QiaoQiao She | Jing Liu | Hua Wu | Haifeng Wang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In this paper, we present DuReader-retrieval, a large-scale Chinese dataset for passage retrieval. DuReader-retrieval contains more than 90K queries and over 8M unique passages from a commercial search engine. To alleviate the shortcomings of other datasets and ensure the quality of our benchmark, we (1) reduce the false negatives in development and test sets by manually annotating results pooled from multiple retrievers, and (2) remove the training queries that are semantically similar to the development and testing queries. Additionally, we provide two out-of-domain testing sets for cross-domain evaluation, as well as a set of human translated queries for for cross-lingual retrieval evaluation. The experiments demonstrate that DuReader-retrieval is challenging and a number of problems remain unsolved, such as the salient phrase mismatch and the syntactic mismatch between queries and paragraphs. These experiments also show that dense retrievers do not generalize well across domains, and cross-lingual retrieval is essentially challenging. DuReader-retrieval is publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval.

pdf
Q-TOD: A Query-driven Task-oriented Dialogue System
Xin Tian | Yingzhan Lin | Mengfei Song | Siqi Bao | Fan Wang | Huang He | Shuqi Sun | Hua Wu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Existing pipelined task-oriented dialogue systems usually have difficulties adapting to unseen domains, whereas end-to-end systems are plagued by large-scale knowledge bases in practice. In this paper, we introduce a novel query-driven task-oriented dialogue system, namely Q-TOD. The essential information from the dialogue context is extracted into a query, which is further employed to retrieve relevant knowledge records for response generation. Firstly, as the query is in the form of natural language and not confined to the schema of the knowledge base, the issue of domain adaption is alleviated remarkably in Q-TOD. Secondly, as the query enables the decoupling of knowledge retrieval from the generation, Q-TOD gets rid of the issue of knowledge base scalability. To evaluate the effectiveness of the proposed Q-TOD, we collect query annotations for three publicly available task-oriented dialogue datasets. Comprehensive experiments verify that Q-TOD outperforms strong baselines and establishes a new state-of-the-art performance on these datasets.

pdf
DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models
Hongyu Zhu | Yan Chen | Jing Yan | Jing Liu | Yu Hong | Ying Chen | Hua Wu | Haifeng Wang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In this paper, we focus on the robustness evaluation of Chinese Question Matching (QM) models. Most of the previous work on analyzing robustness issues focus on just one or a few types of artificial adversarial examples. Instead, we argue that a comprehensive evaluation should be conducted on natural texts, which takes into account the fine-grained linguistic capabilities of QM models. For this purpose, we create a Chinese dataset namely DuQM which contains natural questions with linguistic perturbations to evaluate the robustness of QM models. DuQM contains 3 categories and 13 subcategories with 32 linguistic perturbations. The extensive experiments demonstrate that DuQM has a better ability to distinguish different models. Importantly, the detailed breakdown of evaluation by the linguistic phenomena in DuQM helps us easily diagnose the strength and weakness of different models. Additionally, our experiment results show that the effect of artificial adversarial examples does not work on natural texts. Our baseline codes and a leaderboard are now publicly available.

pdf
PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning
Zeyang Lei | Chao Zhang | Xinchao Xu | Wenquan Wu | Zheng-yu Niu | Hua Wu | Haifeng Wang | Yi Yang | Shuanglong Li
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track

Online advertisement text generation aims at generating attractive and persuasive text ads to appeal to users clicking ads or purchasing products. While pretraining-based models have achieved remarkable success in generating high-quality text ads, some challenges still remain, such as ad generation in low-resource scenarios and training efficiency for multiple ad tasks. In this paper, we propose a novel unified text ad generation framework with multi-task prompt learning, called PLATO-Ad, totackle these problems. Specifically, we design a three-phase transfer learning mechanism to tackle the low-resource ad generation problem. Furthermore, we present a novel multi-task prompt learning mechanism to efficiently utilize a single lightweight model to solve multiple ad generation tasks without loss of performance compared to training a separate model for each task. Finally, we conduct offline and online evaluations and experiment results show that PLATO-Ad significantly outperforms the state-of-the-art on both offline and online metrics. PLATO-Ad has been deployed in a leading advertising platform with 3.5% CTR improvement on search ad descriptions and 10.4% CTR improvement on feed ad titles.

pdf
DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering
Le Qi | Shangwen Lv | Hongyu Li | Jing Liu | Yu Zhang | Qiaoqiao She | Hua Wu | Haifeng Wang | Ting Liu
Findings of the Association for Computational Linguistics: ACL 2022

Open-domain question answering has been used in a wide range of applications, such as web search and enterprise search, which usually takes clean texts extracted from various formats of documents (e.g., web pages, PDFs, or Word documents) as the information source. However, designing different text extraction approaches is time-consuming and not scalable. In order to reduce human cost and improve the scalability of QA systems, we propose and study an Open-domain Document Visual Question Answering (Open-domain DocVQA) task, which requires answering questions based on a collection of document images directly instead of only document texts, utilizing layouts and visual features additionally. Towards this end, we introduce the first Chinese Open-domain DocVQA dataset called DuReadervis, containing about 15K question-answering pairs and 158K document images from the Baidu search engine. There are three main challenges in DuReadervis: (1) long document understanding, (2) noisy texts, and (3) multi-span answer extraction. The extensive experiments demonstrate that the dataset is challenging. Additionally, we propose a simple approach that incorporates the layout and visual features, and the experimental results show the effectiveness of the proposed approach. The dataset and code will be publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-vis.

pdf
Syntax-guided Contrastive Learning for Pre-trained Language Model
Shuai Zhang | Wang Lijie | Xinyan Xiao | Hua Wu
Findings of the Association for Computational Linguistics: ACL 2022

Syntactic information has been proved to be useful for transformer-based pre-trained language models. Previous studies often rely on additional syntax-guided attention components to enhance the transformer, which require more parameters and additional syntactic parsing in downstream tasks. This increase in complexity severely limits the application of syntax-enhanced language model in a wide range of scenarios. In order to inject syntactic knowledge effectively and efficiently into pre-trained language models, we propose a novel syntax-guided contrastive learning method which does not change the transformer architecture. Based on constituency and dependency structures of syntax trees, we design phrase-guided and tree-guided contrastive objectives, and optimize them in the pre-training stage, so as to help the pre-trained language model to capture rich syntactic knowledge in its representations. Experimental results show that our contrastive method achieves consistent improvements in a variety of tasks, including grammatical error detection, entity tasks, structural probing and GLUE. Detailed analysis further verifies that the improvements come from the utilization of syntactic information, and the learned attention weights are more explainable in terms of linguistics.

pdf
DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training
Luyang Huang | Guocheng Niu | Jiachen Liu | Xinyan Xiao | Hua Wu
Findings of the Association for Computational Linguistics: ACL 2022

Due to the limitations of the model structure and pre-training objectives, existing vision-and-language generation models cannot utilize pair-wise images and text through bi-directional generation. In this paper, we propose DU-VLG, a framework which unifies vision-and-language generation as sequence generation problems. DU-VLG is trained with novel dual pre-training tasks: multi-modal denoising autoencoder tasks and modality translation tasks. To bridge the gap between image understanding and generation, we further design a novel commitment loss. We compare pre-training objectives on image captioning and text-to-image generation datasets. Results show that DU-VLG yields better performance than variants trained with uni-directional generation objectives or the variant without the commitment loss. We also obtain higher scores compared to previous state-of-the-art systems on three vision-and-language generation tasks. In addition, human judges further confirm that our model generates real and relevant images as well as faithful and informative captions.

pdf
Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Xinchao Xu | Zhibin Gou | Wenquan Wu | Zheng-Yu Niu | Hua Wu | Haifeng Wang | Shihang Wang
Findings of the Association for Computational Linguistics: ACL 2022

Most of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understanding and memorizing long-term dialogue history information. To address this issue, we present a novel task of Long-term Memory Conversation (LeMon) and then build a new dialogue dataset DuLeMon and a dialogue generation framework with Long-Term Memory (LTM) mechanism (called PLATO-LTM). This LTM mechanism enables our system to accurately extract and continuously update long-term persona memory without requiring multiple-session dialogue datasets for model training. To our knowledge, this is the first attempt to conduct real-time dynamic management of persona information of both parties, including the user and the bot. Results on DuLeMon indicate that PLATO-LTM can significantly outperform baselines in terms of long-term dialogue consistency, leading to better dialogue engagingness.

pdf
UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
Wei Li | Can Gao | Guocheng Niu | Xinyan Xiao | Hao Liu | Jiachen Liu | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: ACL 2022

Vision-Language Pre-training (VLP) has achieved impressive performance on various cross-modal downstream tasks. However, most existing methods can only learn from aligned image-caption data and rely heavily on expensive regional features, which greatly limits their scalability and performance. In this paper, we propose an end-to-end unified-modal pre-training framework, namely UNIMO-2, for joint learning on both aligned image-caption data and unaligned image-only and text-only corpus. We build a unified Transformer model to jointly learn visual representations, textual representations and semantic alignment between images and texts. In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora. The experiments show that our grounded learning method can improve textual and visual semantic alignment for improving performance on various cross-modal tasks. Moreover, benefiting from effective joint modeling of different types of corpora, our model also achieves impressive performance on single-modal visual and textual tasks. Our code and models are public at the UNIMO project page https://unimo-ptm.github.io/.

pdf
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
Siqi Bao | Huang He | Fan Wang | Hua Wu | Haifeng Wang | Wenquan Wu | Zhihua Wu | Zhen Guo | Hua Lu | Xinxian Huang | Xin Tian | Xinchao Xu | Yingzhan Lin | Zheng-Yu Niu
Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022

To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL with up to 11 billion parameters, trained on both Chinese and English social media conversations. To train such large models, we adopt the architecture of unified transformer with high computation and parameter efficiency. In addition, we carry out multi-party aware pre-training to better distinguish the characteristic information in social media conversations. With such designs, PLATO-XL successfully achieves superior performances as compared to other approaches in both Chinese and English chitchat. We further explore the capacity of PLATO-XL on other conversational tasks, such as knowledge grounded dialogue and task-oriented conversation. The experimental results indicate that PLATO-XL obtains state-of-the-art results across multiple conversational tasks, verifying its potential as a foundation model of conversational AI.

pdf
Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards
Yekun Chai | Shuohuan Wang | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: EMNLP 2022

Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did not take full advantage of the over-parameterized characteristics of large pre-trained language models (PLMs). In this paper, we propose Clip-Tuning, a simple yet effective method that adopts diverse frozen “thinned” networks of PLMs to obtain *a mixture of rewards* and thus advance the derivative-free prompt learning. The thinned networks consist of all the hidden units that survive a stationary dropout strategy, whose inference predictions reflect an ensemble of partial views over prompted training samples. Our method outperforms previous gradient-free prompt learning methods and achieves parity with gradient-based counterparts on seven language understanding benchmarks under few-shot settings.

pdf
FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness
Wenhao Wu | Wei Li | Jiachen Liu | Xinyan Xiao | Ziqiang Cao | Sujian Li | Hua Wu
Findings of the Association for Computational Linguistics: EMNLP 2022

Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem.In this paper, we study the faithfulness of existing systems from a new perspective of factual robustness which is the ability to correctly generate factual information over adversarial unfaithful information.We first measure a model’sfactual robustness by its success rate to defend against adversarial attacks when generating factual information.The factual robustness analysis on a wide range of current systems shows its good consistency with human judgments on faithfulness.Inspired by these findings, we propose to improve the faithfulness of a model by enhancing its factual robustness.Specifically, we propose a novel training strategy, namely FRSUM, which teaches the model to defend against both explicit adversarial samples and implicit factual adversarial perturbations.Extensive automatic and human evaluation results show that FRSUM consistently improves the faithfulness of various Seq2Seq models, such as T5, BART.

pdf
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
Qiming Peng | Yinxu Pan | Wenjin Wang | Bin Luo | Zhenyu Zhang | Zhengjie Huang | Yuhui Cao | Weichong Yin | Yongfeng Chen | Yin Zhang | Shikun Feng | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: EMNLP 2022

Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and utilization of layout-centered knowledge, leading to sub-optimal performances. In this paper, we propose ERNIE-Layout, a novel document pre-training solution with layout knowledge enhancement in the whole workflow, to learn better representations that combine the features from text, layout, and image. Specifically, we first rearrange input sequences in the serialization stage, and then present a correlative pre-training task, reading order prediction, to learn the proper reading order of documents. To improve the layout awareness of the model, we integrate a spatial-aware disentangled attention into the multi-modal transformer and a replaced regions prediction task into the pre-training phase. Experimental results show that ERNIE-Layout achieves superior performance on various downstream tasks, setting new state-of-the-art on key information extraction, document image classification, and document question answering datasets. The code and models are publicly available at PaddleNLP.

2021

pdf
Discovering Dialog Structure Graph for Coherent Dialog Generation
Jun Xu | Zeyang Lei | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Learning discrete dialog structure graph from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation. However, this problem is less studied in open-domain dialogue. In this paper, we conduct unsupervised discovery of discrete dialog structure from chitchat corpora, and then leverage it to facilitate coherent dialog generation in downstream systems. To this end, we present an unsupervised model, Discrete Variational Auto-Encoder with Graph Neural Network (DVAE-GNN), to discover discrete hierarchical latent dialog states (at the level of both session and utterance) and their transitions from corpus as a dialog structure graph. Then we leverage it as background knowledge to facilitate dialog management in a RL based dialog system. Experimental results on two benchmark corpora confirm that DVAE-GNN can discover meaningful dialog structure graph, and the use of dialog structure as background knowledge can significantly improve multi-turn coherence.

pdf
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Wei Li | Can Gao | Guocheng Niu | Xinyan Xiao | Hao Liu | Jiachen Liu | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e., text or image) or limited multi-modal data (i.e., image-text pairs). In this work, we propose a UNIfied-MOdal pre-training architecture, namely UNIMO, which can effectively adapt to both single-modal and multi-modal understanding and generation tasks. Large scale of free text corpus and image collections are utilized to improve the capability of visual and textual understanding, and cross-modal contrastive learning (CMCL) is leveraged to align the textual and visual information into a unified semantic space, over a corpus of image-text pairs augmented with related images and texts. With the help of rich non-paired single-modal data, our model is able to learn more generalizable representations, by allowing textual knowledge and visual knowledge to enhance each other in the unified semantic space. The experimental results show that UNIMO greatly improves the performance of several single-modal and multi-modal downstream tasks. Our code and pre-trained models are public at https://github.com/PaddlePaddle/Research/tree/master/NLP/UNIMO.

pdf
ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
SiYu Ding | Junyuan Shang | Shuohuan Wang | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Transformers are not suited for processing long documents, due to their quadratically increasing memory and time consumption. Simply truncating a long document or applying the sparse attention mechanism will incur the context fragmentation problem or lead to an inferior modeling capability against comparable model sizes. In this paper, we propose ERNIE-Doc, a document-level language pretraining model based on Recurrence Transformers. Two well-designed techniques, namely the retrospective feed mechanism and the enhanced recurrence mechanism, enable ERNIE-Doc, which has a much longer effective context length, to capture the contextual information of a complete document. We pretrain ERNIE-Doc to explicitly learn the relationships among segments with an additional document-aware segment-reordering objective. Various experiments were conducted on both English and Chinese document-level tasks. ERNIE-Doc improved the state-of-the-art language modeling result of perplexity to 16.8 on WikiText-103. Moreover, it outperformed competitive pretraining models by a large margin on most language understanding tasks, such as text classification and question answering.

pdf
BASS: Boosting Abstractive Summarization with Unified Semantic Graph
Wenhao Wu | Wei Li | Xinyan Xiao | Jiachen Liu | Ziqiang Cao | Sujian Li | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Abstractive summarization for long-document or multi-document remains challenging for the Seq2Seq architecture, as Seq2Seq is not good at analyzing long-distance relations in text. In this paper, we present BASS, a novel framework for Boosting Abstractive Summarization based on a unified Semantic graph, which aggregates co-referent phrases distributing across a long range of context and conveys rich relations between phrases. Further, a graph-based encoder-decoder model is proposed to improve both the document representation and summary generation process by leveraging the graph structure. Specifically, several graph augmentation methods are designed to encode both the explicit and implicit relations in the text while the graph-propagation attention mechanism is developed in the decoder to select salient content into the summary. Empirical results show that the proposed architecture brings substantial improvements for both long-document and multi-document summarization tasks.

pdf
DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
Hongxuan Tang | Hongyu Li | Jing Liu | Yu Hong | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements. However, most of the neural MRC models are still far from robust and fail to generalize well in real-world applications. In order to comprehensively verify the robustness and generalization of MRC models, we introduce a real-world Chinese dataset – DuReader_robust . It is designed to evaluate the MRC models from three aspects: over-sensitivity, over-stability and generalization. Comparing to previous work, the instances in DuReader_robust are natural texts, rather than the altered unnatural texts. It presents the challenges when applying MRC models to real-world applications. The experimental results show that MRC models do not perform well on the challenge test set. Moreover, we analyze the behavior of existing models on the challenge test set, which may provide suggestions for future model development. The dataset and codes are publicly available at https://github.com/baidu/DuReader.

pdf
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
Dongling Xiao | Yu-Kun Li | Han Zhang | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Coarse-grained linguistic information, such as named entities or phrases, facilitates adequately representation learning in pre-training. Previous works mainly focus on extending the objective of BERT’s Masked Language Modeling (MLM) from masking individual tokens to contiguous sequences of n tokens. We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information. As an alternative, we propose ERNIE-Gram, an explicitly n-gram masking method to enhance the integration of coarse-grained information into pre-training. In ERNIE-Gram, n-grams are masked and predicted directly using explicit n-gram identities rather than contiguous sequences of n tokens. Furthermore, ERNIE-Gram employs a generator model to sample plausible n-gram identities as optional n-gram masks and predict them in both coarse-grained and fine-grained manners to enable comprehensive n-gram prediction and relation modeling. We pre-train ERNIE-Gram on English and Chinese text corpora and fine-tune on 19 downstream tasks. Experimental results show that ERNIE-Gram outperforms previous pre-training models like XLNet and RoBERTa by a large margin, and achieves comparable results with state-of-the-art methods. The source codes and pre-trained models have been released at https://github.com/PaddlePaddle/ERNIE.

pdf
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
Yingqi Qu | Yuchen Ding | Jing Liu | Kai Liu | Ruiyang Ren | Wayne Xin Zhao | Daxiang Dong | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of questions and passages for semantic matching. However, it is difficult to effectively train a dual-encoder due to the challenges including the discrepancy between training and inference, the existence of unlabeled positives and limited training data. To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. We make three major technical contributions in RocketQA, namely cross-batch negatives, denoised hard negatives and data augmentation. The experiment results show that RocketQA significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions. We also conduct extensive experiments to examine the effectiveness of the three strategies in RocketQA. Besides, we demonstrate that the performance of end-to-end QA can be improved based on our RocketQA retriever.

pdf bib
Proceedings of the 20th Chinese National Conference on Computational Linguistics
Sheng Li (李生) | Maosong Sun (孙茂松) | Yang Liu (刘洋) | Hua Wu (吴华) | Kang Liu (刘康) | Wanxiang Che (车万翔) | Shizhu He (何世柱) | Gaoqi Rao (饶高琦)
Proceedings of the 20th Chinese National Conference on Computational Linguistics

pdf
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
Ruiyang Ren | Shangwen Lv | Yingqi Qu | Jing Liu | Wayne Xin Zhao | QiaoQiao She | Hua Wu | Haifeng Wang | Ji-Rong Wen
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Correcting Chinese Spelling Errors with Phonetic Pre-training
Ruiqing Zhang | Chao Pang | Chuanqiang Zhang | Shuohuan Wang | Zhongjun He | Yu Sun | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
Siqi Bao | Huang He | Fan Wang | Hua Wu | Haifeng Wang | Wenquan Wu | Zhen Guo | Zhibin Liu | Xinchao Xu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Mixup Decoding for Diverse Machine Translation
Jicheng Li | Pengzhi Gao | Xuanfu Wu | Yang Feng | Zhongjun He | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: EMNLP 2021

Diverse machine translation aims at generating various target language translations for a given source language sentence. To leverage the linear relationship in the sentence latent space introduced by the mixup training, we propose a novel method, MixDiversity, to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding. To further improve the faithfulness and diversity of the translations, we propose two simple but effective approaches to select diverse sentence pairs in the training corpus and adjust the interpolation weight for each pair correspondingly. Moreover, by controlling the interpolation weight, our method can achieve the trade-off between faithfulness and diversity without any additional training, which is required in most of the previous methods. Experiments on WMT’16 en-ro, WMT’14 en-de, and WMT’17 zh-en are conducted to show that our method substantially outperforms all previous diverse machine translation methods.

pdf
ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora
Xuan Ouyang | Shuohuan Wang | Chao Pang | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is generally acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose Ernie-M, a new training method that encourages the model to align the representation of multiple languages with monolingual corpora, to overcome the constraint that the parallel corpus size places on the model performance. Our key insight is to integrate back-translation into the pre-training process. We generate pseudo-parallel sentence pairs on a monolingual corpus to enable the learning of semantic alignments between different languages, thereby enhancing the semantic modeling of cross-lingual models. Experimental results show that Ernie-M outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-lingual downstream tasks. The codes and pre-trained models will be made publicly available.

pdf
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
Ruiyang Ren | Yingqi Qu | Jing Liu | Wayne Xin Zhao | QiaoQiao She | Hua Wu | Haifeng Wang | Ji-Rong Wen
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to jointly optimize them in order to achieve mutual improvement. In this paper, we propose a novel joint training approach for dense passage retrieval and passage reranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dynamic distillation, the retriever and the re-ranker can be adaptively improved according to each other’s relevance information. We also propose a hybrid data augmentation strategy to construct diverse training instances for listwise training approach. Extensive experiments show the effectiveness of our approach on both MSMARCO and Natural Questions datasets. Our code is available at https://github.com/PaddlePaddle/RocketQA.

pdf
SgSum:Transforming Multi-document Summarization into Sub-graph Selection
Moye Chen | Wei Li | Jiachen Liu | Xinyan Xiao | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Most of existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary, which have two main drawbacks: (1) neglecting both the intra and cross-document relations between sentences; (2) neglecting the coherence and conciseness of the whole summary. In this paper, we propose a novel MDS framework (SgSum) to formulate the MDS task as a sub-graph selection problem, in which source documents are regarded as a relation graph of sentences (e.g., similarity graph or discourse graph) and the candidate summaries are its sub-graphs. Instead of selecting salient sentences, SgSum selects a salient sub-graph from the relation graph as the summary. Comparing with traditional methods, our method has two main advantages: (1) the relations between sentences are captured by modeling both the graph structure of the whole document set and the candidate sub-graphs; (2) directly outputs an integrate summary in the form of sub-graph which is more informative and coherent. Extensive experiments on MultiNews and DUC datasets show that our proposed method brings substantial improvements over several strong baselines. Human evaluation results also demonstrate that our model can produce significantly more coherent and informative summaries compared with traditional MDS methods. Moreover, the proposed architecture has strong transfer ability from single to multi-document input, which can reduce the resource bottleneck in MDS tasks.

pdf
DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation
Zeming Liu | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In this paper, we provide a bilingual parallel human-to-human recommendation dialog dataset (DuRecDial 2.0) to enable researchers to explore a challenging task of multilingual and cross-lingual conversational recommendation. The difference between DuRecDial 2.0 and existing conversational recommendation datasets is that the data item (Profile, Goal, Knowledge, Context, Response) in DuRecDial 2.0 is annotated in two languages, both English and Chinese, while other datasets are built with the setting of a single language. We collect 8.2k dialogs aligned across English and Chinese languages (16.5k dialogs and 255k utterances in total) that are annotated by crowdsourced workers with strict quality control procedure. We then build monolingual, multilingual, and cross-lingual conversational recommendation baselines on DuRecDial 2.0. Experiment results show that the use of additional English data can bring performance improvement for Chinese conversational recommendation, indicating the benefits of DuRecDial 2.0. Finally, this dataset provides a challenging testbed for future studies of monolingual, multilingual, and cross-lingual conversational recommendation.

pdf
Fine-grained Entity Typing via Label Reasoning
Qing Liu | Hongyu Lin | Xinyan Xiao | Xianpei Han | Le Sun | Hua Wu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types. In this paper, we argue that the implicitly entailed extrinsic and intrinsic dependencies between labels can provide critical knowledge to tackle the above challenges. To this end, we propose Label Reasoning Network(LRN), which sequentially reasons fine-grained entity labels by discovering and exploiting label dependencies knowledge entailed in the data. Specifically, LRN utilizes an auto-regressive network to conduct deductive reasoning and a bipartite attribute graph to conduct inductive reasoning between labels, which can effectively model, learn and reason complex label dependencies in a sequence-to-set, end-to-end manner. Experiments show that LRN achieves the state-of-the-art performance on standard ultra fine-grained entity typing benchmarks, and can also resolve the long tail label problem effectively.

pdf
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing
Kun Wu | Lijie Wang | Zhenghua Li | Ao Zhang | Xinyan Xiao | Hua Wu | Min Zhang | Haifeng Wang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Data augmentation has attracted a lot of research attention in the deep learning era for its ability in alleviating data sparseness. The lack of labeled data for unseen evaluation databases is exactly the major challenge for cross-domain text-to-SQL parsing. Previous works either require human intervention to guarantee the quality of generated data, or fail to handle complex SQL queries. This paper presents a simple yet effective data augmentation framework. First, given a database, we automatically produce a large number of SQL queries based on an abstract syntax tree grammar. For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries. Second, we propose a hierarchical SQL-to-question generation model to obtain high-quality natural language questions, which is the major contribution of this work. Finally, we design a simple sampling strategy that can greatly improve training efficiency given large amounts of generated data. Experiments on three cross-domain datasets, i.e., WikiSQL and Spider in English, and DuSQL in Chinese, show that our proposed data augmentation framework can consistently improve performance over strong baselines, and the hierarchical generation component is the key for the improvement.

pdf
Amendable Generation for Dialogue State Tracking
Xin Tian | Liankai Huang | Yingzhan Lin | Siqi Bao | Huang He | Yunyi Yang | Hua Wu | Fan Wang | Shuqi Sun
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI

In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current turn are prone to be carried over to the next turn, causing error propagation. In this paper, we propose a novel Amendable Generation for Dialogue State Tracking (AG-DST), which contains a two-pass generation process: (1) generating a primitive dialogue state based on the dialogue of the current turn and the previous dialogue state, and (2) amending the primitive dialogue state from the first pass. With the additional amending generation pass, our model is tasked to learn more robust dialogue state tracking by amending the errors that still exist in the primitive dialogue state, which plays the role of reviser in the double-checking process and alleviates unnecessary error propagation. Experimental results show that AG-DST significantly outperforms previous works in two active DST datasets (MultiWOZ 2.2 and WOZ 2.0), achieving new state-of-the-art performances.

pdf
PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling
Xinxian Huang | Huang He | Siqi Bao | Fan Wang | Hua Wu | Haifeng Wang
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI

Large-scale conversation models are turning to leveraging external knowledge to improve the factual accuracy in response generation. Considering the infeasibility to annotate the external knowledge for large-scale dialogue corpora, it is desirable to learn the knowledge selection and response generation in an unsupervised manner. In this paper, we propose PLATO-KAG (Knowledge-Augmented Generation), an unsupervised learning approach for end-to-end knowledge-grounded conversation modeling. For each dialogue context, the top-k relevant knowledge elements are selected and then employed in knowledge-grounded response generation. The two components of knowledge selection and response generation are optimized jointly and effectively under a balanced objective. Experimental results on two publicly available datasets validate the superiority of PLATO-KAG.

pdf bib
Proceedings of the Second Workshop on Automatic Simultaneous Translation
Hua Wu | Colin Cherry | Liang Huang | Zhongjun He | Qun Liu | Maha Elbayad | Mark Liberman | Haifeng Wang | Mingbo Ma | Ruiqing Zhang
Proceedings of the Second Workshop on Automatic Simultaneous Translation

pdf
BSTC: A Large-Scale Chinese-English Speech Translation Dataset
Ruiqing Zhang | Xiyang Wang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Zhi Li | Haifeng Wang | Ying Chen | Qinfei Li
Proceedings of the Second Workshop on Automatic Simultaneous Translation

This paper presents BSTC (Baidu Speech Translation Corpus), a large-scale Chinese-English speech translation dataset. This dataset is constructed based on a collection of licensed videos of talks or lectures, including about 68 hours of Mandarin data, their manual transcripts and translations into English, as well as automated transcripts by an automatic speech recognition (ASR) model. We have further asked three experienced interpreters to simultaneously interpret the testing talks in a mock conference setting. This corpus is expected to promote the research of automatic simultaneous translation as well as the development of practical systems. We have organized simultaneous translation tasks and used this corpus to evaluate automatic simultaneous translation systems.

pdf
Findings of the Second Workshop on Automatic Simultaneous Translation
Ruiqing Zhang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the Second Workshop on Automatic Simultaneous Translation

This paper presents the results of the shared task of the 2nd Workshop on Automatic Simultaneous Translation (AutoSimTrans). The task includes two tracks, one for text-to-text translation and one for speech-to-text, requiring participants to build systems to translate from either the source text or speech into the target text. Different from traditional machine translation, the AutoSimTrans shared task evaluates not only translation quality but also latency. We propose a metric “Monotonic Optimal Sequence” (MOS) considering both quality and latency to rank the submissions. We also discuss some important open issues in simultaneous translation.

2020

pdf bib
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
Kam-Fai Wong | Kevin Knight | Hua Wu
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

pdf bib
Proceedings of the First Workshop on Automatic Simultaneous Translation
Hua Wu | Colin Cherry | Liang Huang | Zhongjun He | Mark Liberman | James Cross | Yang Liu
Proceedings of the First Workshop on Automatic Simultaneous Translation

pdf
PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
Siqi Bao | Huang He | Fan Wang | Hua Wu | Haifeng Wang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering. In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation. We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation. Two reciprocal tasks of response generation and latent act recognition are designed and carried out simultaneously within a shared network. Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.

pdf
Towards Conversational Recommendation over Multi-Type Dialogs
Zeming Liu | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che | Ting Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We focus on the study of conversational recommendation in the context of multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e.g., QA) to a recommendation dialog, taking into account user’s interests and feedback. To facilitate the study of this task, we create a human-to-human Chinese dialog dataset DuRecDial (about 10k dialogs, 156k utterances), where there are multiple sequential dialogs for a pair of a recommendation seeker (user) and a recommender (bot). In each dialog, the recommender proactively leads a multi-type dialog to approach recommendation targets and then makes multiple recommendations with rich interaction behavior. This dataset allows us to systematically investigate different parts of the overall problem, e.g., how to naturally lead a dialog, how to interact with users for recommendation. Finally we establish baseline results on DuRecDial for future studies.

pdf
Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation
Jun Xu | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che | Ting Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

To address the challenge of policy learning in open-domain multi-turn conversation, we propose to represent prior information about dialog transitions as a graph and learn a graph grounded dialog policy, aimed at fostering a more coherent and controllable dialog. To this end, we first construct a conversational graph (CG) from dialog corpora, in which there are vertices to represent “what to say” and “how to say”, and edges to represent natural transition between a message (the last utterance in a dialog context) and its response. We then present a novel CG grounded policy learning framework that conducts dialog flow planning by graph traversal, which learns to identify a what-vertex and a how-vertex from the CG at each turn to guide response generation. In this way, we effectively leverage the CG to facilitate policy learning as follows: (1) it enables more effective long-term reward design, (2) it provides high-quality candidate actions, and (3) it gives us more control over the policy. Results on two benchmark corpora demonstrate the effectiveness of this framework.

pdf
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis
Hao Tian | Can Gao | Xinyan Xiao | Hao Liu | Bolei He | Hua Wu | Haifeng Wang | Feng Wu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Recently, sentiment analysis has seen remarkable advance with the help of pre-training approaches. However, sentiment knowledge, such as sentiment words and aspect-sentiment pairs, is ignored in the process of pre-training, despite the fact that they are widely used in traditional sentiment analysis approaches. In this paper, we introduce Sentiment Knowledge Enhanced Pre-training (SKEP) in order to learn a unified sentiment representation for multiple sentiment analysis tasks. With the help of automatically-mined knowledge, SKEP conducts sentiment masking and constructs three sentiment knowledge prediction objectives, so as to embed sentiment information at the word, polarity and aspect level into pre-trained sentiment representation. In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair. Experiments on three kinds of sentiment tasks show that SKEP significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets. We release our code at https://github.com/baidu/Senta.

pdf
Leveraging Graph to Improve Abstractive Multi-Document Summarization
Wei Li | Xinyan Xiao | Jiachen Liu | Hua Wu | Haifeng Wang | Junping Du
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents such as similarity graph and discourse graph, to more effectively process multiple input documents and produce abstractive summaries. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. Our model can also take advantage of graphs to guide the summary generation process, which is beneficial for generating coherent and concise summaries. Furthermore, pre-trained language models can be easily combined with our model, which further improve the summarization performance significantly. Empirical results on the WikiSum and MultiNews dataset show that the proposed architecture brings substantial improvements over several strong baselines.

pdf
Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer
Chulun Zhou | Liangyu Chen | Jiachen Liu | Xinyan Xiao | Jinsong Su | Sheng Guo | Hua Wu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style, they are unable to yield desirable output sentences. In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the target style for unsupervised style transfer. Specifically, we first pretrain a style classifier, where the relevance of each input word to the original style can be quantified via layer-wise relevance propagation. In a denoising auto-encoding manner, we train an attentional Seq2seq model to reconstruct input sentences and repredict word-level previously-quantified style relevance simultaneously. In this way, this model is endowed with the ability to automatically predict the style relevance of each output word. Then, we equip the decoder of this model with a neural style component to exploit the predicted wordlevel style relevance for better style transfer. Particularly, we fine-tune this model using a carefully-designed objective function involving style transfer, style relevance consistency, content preservation and fluency modeling loss terms. Experimental results show that our proposed model achieves state-of-the-art performance in terms of both transfer accuracy and content preservation.

pdf
Syntactic and Semantic-driven Learning for Open Information Extraction
Jialong Tang | Yaojie Lu | Hongyu Lin | Xianpei Han | Le Sun | Xinyan Xiao | Hua Wu
Findings of the Association for Computational Linguistics: EMNLP 2020

One of the biggest bottlenecks in building accurate, high coverage neural open IE systems is the need for large labelled corpora. The diversity of open domain corpora and the variety of natural language expressions further exacerbate this problem. In this paper, we propose a syntactic and semantic-driven learning approach, which can learn neural open IE models without any human-labelled data by leveraging syntactic and semantic knowledge as noisier, higher-level supervision. Specifically, we first employ syntactic patterns as data labelling functions and pretrain a base model using the generated labels. Then we propose a syntactic and semantic-driven reinforcement learning algorithm, which can effectively generalize the base model to open situations with high accuracy. Experimental results show that our approach significantly outperforms the supervised counterparts, and can even achieve competitive performance to supervised state-of-the-art (SoA) model.

pdf
Learning Adaptive Segmentation Policy for Simultaneous Translation
Ruiqing Zhang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Balancing accuracy and latency is a great challenge for simultaneous translation. To achieve high accuracy, the model usually needs to wait for more streaming text before translation, which results in increased latency. However, keeping low latency would probably hurt accuracy. Therefore, it is essential to segment the ASR output into appropriate units for translation. Inspired by human interpreters, we propose a novel adaptive segmentation policy for simultaneous translation. The policy learns to segment the source text by considering possible translations produced by the translation model, maintaining consistency between the segmentation and translation. Experimental results on Chinese-English and German-English translation show that our method achieves a better accuracy-latency trade-off over recently proposed state-of-the-art methods.

pdf
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
Lijie Wang | Ao Zhang | Kun Wu | Ke Sun | Zhenghua Li | Hua Wu | Min Zhang | Haifeng Wang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Due to the lack of labeled data, previous research on text-to-SQL parsing mainly focuses on English. Representative English datasets include ATIS, WikiSQL, Spider, etc. This paper presents DuSQL, a larges-scale and pragmatic Chinese dataset for the cross-domain text-to-SQL task, containing 200 databases, 813 tables, and 23,797 question/SQL pairs. Our new dataset has three major characteristics. First, by manually analyzing questions from several representative applications, we try to figure out the true distribution of SQL queries in real-life needs. Second, DuSQL contains a considerable proportion of SQL queries involving row or column calculations, motivated by our analysis on the SQL query distributions. Finally, we adopt an effective data construction framework via human-computer collaboration. The basic idea is automatically generating SQL queries based on the SQL grammar and constrained by the given database. This paper describes in detail the construction process and data statistics of DuSQL. Moreover, we present and compare performance of several open-source text-to-SQL parsers with minor modification to accommodate Chinese, including a simple yet effective extension to IRNet for handling calculation SQL queries.

pdf
Diversified Multiple Instance Learning for Document-Level Multi-Aspect Sentiment Classification
Yunjie Ji | Hao Liu | Bolei He | Xinyan Xiao | Hua Wu | Yanhua Yu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Neural Document-level Multi-aspect Sentiment Classification (DMSC) usually requires a lot of manual aspect-level sentiment annotations, which is time-consuming and laborious. As document-level sentiment labeled data are widely available from online service, it is valuable to perform DMSC with such free document-level annotations. To this end, we propose a novel Diversified Multiple Instance Learning Network (D-MILN), which is able to achieve aspect-level sentiment classification with only document-level weak supervision. Specifically, we connect aspect-level and document-level sentiment by formulating this problem as multiple instance learning, providing a way to learn aspect-level classifier from the back propagation of document-level supervision. Two diversified regularizations are further introduced in order to avoid the overfitting on document-level signals during training. Diversified textual regularization encourages the classifier to select aspect-relevant snippets, and diversified sentimental regularization prevents the aspect-level sentiments from being overly consistent with document-level sentiment. Experimental results on TripAdvisor and BeerAdvocate datasets show that D-MILN remarkably outperforms recent weakly-supervised baselines, and is also comparable to the supervised method.

2019

pdf
ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification
Wei Jia | Dai Dai | Xinyan Xiao | Hua Wu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Distant supervision is widely used in relation classification in order to create large-scale training data by aligning a knowledge base with an unlabeled corpus. However, it also introduces amounts of noisy labels where a contextual sentence actually does not express the labeled relation. In this paper, we propose ARNOR, a novel Attention Regularization based NOise Reduction framework for distant supervision relation classification. ARNOR assumes that a trustable relation label should be explained by the neural attention model. Specifically, our ARNOR framework iteratively learns an interpretable model and utilizes it to select trustable instances. We first introduce attention regularization to force the model to pay attention to the patterns which explain the relation labels, so as to make the model more interpretable. Then, if the learned model can clearly locate the relation patterns of a candidate instance in the training set, we will select it as a trustable instance for further training step. According to the experiments on NYT data, our ARNOR framework achieves significant improvements over state-of-the-art methods in both relation classification performance and noise reduction effect.

pdf
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension
An Yang | Quan Wang | Jing Liu | Kai Liu | Yajuan Lyu | Hua Wu | Qiaoqiao She | Sujian Li
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Machine reading comprehension (MRC) is a crucial and challenging task in NLP. Recently, pre-trained language models (LMs), especially BERT, have achieved remarkable success, presenting new state-of-the-art results in MRC. In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC. We introduce KT-NET, which employs an attention mechanism to adaptively select desired knowledge from KBs, and then fuses selected knowledge with BERT to enable context- and knowledge-aware predictions. We believe this would combine the merits of both deep LMs and curated KBs towards better MRC. Experimental results indicate that KT-NET offers significant and consistent improvements over BERT, outperforming competitive baselines on ReCoRD and SQuAD1.1 benchmarks. Notably, it ranks the 1st place on the ReCoRD leaderboard, and is also the best single model on the SQuAD1.1 leaderboard at the time of submission (March 4th, 2019).

pdf
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework
Mingbo Ma | Liang Huang | Hao Xiong | Renjie Zheng | Kaibo Liu | Baigong Zheng | Chuanqiang Zhang | Zhongjun He | Hairong Liu | Xing Li | Hua Wu | Haifeng Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Simultaneous translation, which translates sentences before they are finished, is use- ful in many scenarios but is notoriously dif- ficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we pro- pose a novel prefix-to-prefix framework for si- multaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very sim- ple yet surprisingly effective “wait-k” policy trained to generate the target sentence concur- rently with the source sentence, but always k words behind. Experiments show our strat- egy achieves low latency and reasonable qual- ity (compared to full-sentence translation) on 4 directions: zh↔en and de↔en.

pdf
Proactive Human-Machine Conversation with Explicit Conversation Goal
Wenquan Wu | Zhen Guo | Xiangyang Zhou | Hua Wu | Xiyuan Zhang | Rongzhong Lian | Haifeng Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Though great progress has been made for human-machine conversation, current dialogue system is still in its infancy: it usually converses passively and utters words more as a matter of response, rather than on its own initiatives. In this paper, we take a radical step towards building a human-like conversational agent: endowing it with the ability of proactively leading the conversation (introducing a new topic or maintaining the current topic). To facilitate the development of such conversation systems, we create a new dataset named Konv where one acts as a conversation leader and the other acts as the follower. The leader is provided with a knowledge graph and asked to sequentially change the discussion topics, following the given conversation goal, and meanwhile keep the dialogue as natural and engaging as possible. Konv enables a very challenging task as the model needs to both understand dialogue and plan over the given knowledge graph. We establish baseline results on this dataset (about 270K utterances and 30k dialogues) using several state-of-the-art models. Experimental results show that dialogue models that plan over the knowledge graph can make full use of related knowledge to generate more diverse multi-turn conversations. The baseline systems along with the dataset are publicly available.

pdf
Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment
Siqi Bao | Huang He | Fan Wang | Rongzhong Lian | Hua Wu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other. For the sake of rational knowledge utilization and coherent conversation flow, a dialogue strategy which controls knowledge selection is instantiated and continuously adapted via reinforcement learning. Under the deployed strategy, knowledge grounded conversations are conducted with two dialogue agents. The generated dialogues are comprehensively evaluated on aspects like informativeness and coherence, which are aligned with our objective and human instinct. These assessments are integrated as a compound reward to guide the evolution of dialogue strategy via policy gradient. Comprehensive experiments have been carried out on the publicly available dataset, demonstrating that the proposed method outperforms the other state-of-the-art approaches significantly.

pdf
Enhancing Local Feature Extraction with Global Representation for Neural Text Classification
Guocheng Niu | Hengru Xu | Bolei He | Xinyan Xiao | Hua Wu | Sheng Gao
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

For text classification, traditional local feature driven models learn long dependency by deeply stacking or hybrid modeling. This paper proposes a novel Encoder1-Encoder2 architecture, where global information is incorporated into the procedure of local feature extraction from scratch. In particular, Encoder1 serves as a global information provider, while Encoder2 performs as a local feature extractor and is directly fed into the classifier. Meanwhile, two modes are also designed for their interaction. Thanks to the awareness of global information, our method is able to learn better instance specific local features and thus avoids complicated upper operations. Experiments conducted on eight benchmark datasets demonstrate that our proposed architecture promotes local feature driven models by a substantial margin and outperforms the previous best models in the fully-supervised setting.

pdf
Multi-agent Learning for Neural Machine Translation
Tianchi Bi | Hao Xiong | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decod- ing from left to right and the other decoding in the opposite direction. In this paper, we extend the training framework to the multi-agent sce- nario by introducing diverse agents in an in- teractive updating process. At training time, each agent learns advanced knowledge from others, and they work together to improve translation quality. Experimental results on NIST Chinese-English, IWSLT 2014 German- English, WMT 2014 English-German and large-scale Chinese-English translation tasks indicate that our approach achieves absolute improvements over the strong baseline sys- tems and shows competitive performance on all tasks.

pdf
Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs
Zhibin Liu | Zheng-Yu Niu | Hua Wu | Haifeng Wang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open domain conversation generation, in which graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning to effectively capture conversation flow, which is more explainable and flexible in comparison with previous works. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate the effectiveness of our system on two datasets in comparison with state-of-the-art models.

pdf
D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension
Hongyu Li | Xiyuan Zhang | Yibing Liu | Yiming Zhang | Quan Wang | Xiangyang Zhou | Jing Liu | Hua Wu | Haifeng Wang
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

In this paper, we introduce a simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models. Our system is built on a framework of pretraining and fine-tuning, namely D-NET. The techniques of pre-trained language models and multi-task learning are explored to improve the generalization of MRC models and we conduct experiments to examine the effectiveness of these strategies. Our system is ranked at top 1 of all the participants in terms of averaged F1 score. Our codes and models will be released at PaddleNLP.

pdf
Baidu Neural Machine Translation Systems for WMT19
Meng Sun | Bojian Jiang | Hao Xiong | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

In this paper we introduce the systems Baidu submitted for the WMT19 shared task on Chinese<->English news translation. Our systems are based on the Transformer architecture with some effective improvements. Data selection, back translation, data augmentation, knowledge distillation, domain adaptation, model ensemble and re-ranking are employed and proven effective in our experiments. Our Chinese->English system achieved the highest case-sensitive BLEU score among all constrained submissions, and our English->Chinese system ranked the second in all submissions.

2018

pdf
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network
Xiangyang Zhou | Lu Li | Daxiang Dong | Yi Liu | Ying Chen | Wayne Xin Zhao | Dianhai Yu | Hua Wu
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context. In this paper, we investigate matching a response with its multi-turn context using dependency information based entirely on attention. Our solution is inspired by the recently proposed Transformer in machine translation (Vaswani et al., 2017) and we extend the attention mechanism in two ways. First, we construct representations of text segments at different granularities solely with stacked self-attention. Second, we try to extract the truly matched segment pairs with attention across the context and response. We jointly introduce those two kinds of attention in one uniform neural network. Experiments on two large-scale multi-turn response selection tasks show that our proposed model significantly outperforms the state-of-the-art models.

pdf
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
Yizhong Wang | Kai Liu | Jing Liu | Wei He | Yajuan Lyu | Hua Wu | Sujian Li | Haifeng Wang
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine. Compared with MRC on a single passage, multi-passage MRC is more challenging, since we are likely to get multiple confusing answer candidates from different passages. To address this problem, we propose an end-to-end neural model that enables those answer candidates from different passages to verify each other based on their content representations. Specifically, we jointly train three modules that can predict the final answer based on three factors: the answer boundary, the answer content and the cross-passage answer verification. The experimental results show that our method outperforms the baseline by a large margin and achieves the state-of-the-art performance on the English MS-MARCO dataset and the Chinese DuReader dataset, both of which are designed for MRC in real-world settings.

pdf
DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
Wei He | Kai Liu | Jing Liu | Yajuan Lyu | Shiqi Zhao | Xinyan Xiao | Yuan Liu | Yizhong Wang | Hua Wu | Qiaoqiao She | Xuan Liu | Tian Wu | Haifeng Wang
Proceedings of the Workshop on Machine Reading for Question Answering

This paper introduces DuReader, a new large-scale, open-domain Chinese machine reading comprehension (MRC) dataset, designed to address real-world MRC. DuReader has three advantages over previous MRC datasets: (1) data sources: questions and documents are based on Baidu Search and Baidu Zhidao; answers are manually generated. (2) question types: it provides rich annotations for more question types, especially yes-no and opinion questions, that leaves more opportunity for the research community. (3) scale: it contains 200K questions, 420K answers and 1M documents; it is the largest Chinese MRC dataset so far. Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements. To help the community make these improvements, both DuReader and baseline systems have been posted online. We also organize a shared competition to encourage the exploration of more models. Since the release of the task, there are significant improvements over the baselines.

pdf
Addressing Troublesome Words in Neural Machine Translation
Yang Zhao | Jiajun Zhang | Zhongjun He | Chengqing Zong | Hua Wu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

One of the weaknesses of Neural Machine Translation (NMT) is in handling lowfrequency and ambiguous words, which we refer as troublesome words. To address this problem, we propose a novel memoryenhanced NMT method. First, we investigate different strategies to define and detect the troublesome words. Then, a contextual memory is constructed to memorize which target words should be produced in what situations. Finally, we design a hybrid model to dynamically access the contextual memory so as to correctly translate the troublesome words. The extensive experiments on Chinese-to-English and English-to-German translation tasks demonstrate that our method significantly outperforms the strong baseline models in translation quality, especially in handling troublesome words.

2017

pdf
An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge
Yanchao Hao | Yuanzhe Zhang | Kang Liu | Shizhu He | Zhanyi Liu | Hua Wu | Jun Zhao
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

With the rapid growth of knowledge bases (KBs) on the web, how to take full advantage of them becomes increasingly important. Question answering over knowledge base (KB-QA) is one of the promising approaches to access the substantial knowledge. Meanwhile, as the neural network-based (NN-based) methods develop, NN-based KB-QA has already achieved impressive results. However, previous work did not put more emphasis on question representation, and the question is converted into a fixed vector regardless of its candidate answers. This simple representation strategy is not easy to express the proper information in the question. Hence, we present an end-to-end neural network model to represent the questions and their corresponding scores dynamically according to the various candidate answer aspects via cross-attention mechanism. In addition, we leverage the global knowledge inside the underlying KB, aiming at integrating the rich KB information into the representation of the answers. As a result, it could alleviates the out-of-vocabulary (OOV) problem, which helps the cross-attention model to represent the question more precisely. The experimental results on WebQuestions demonstrate the effectiveness of the proposed approach.

2016

pdf
Multi-view Response Selection for Human-Computer Conversation
Xiangyang Zhou | Daxiang Dong | Hua Wu | Shiqi Zhao | Dianhai Yu | Hao Tian | Xuan Liu | Rui Yan
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf
Chinese Poetry Generation with Planning based Neural Network
Zhe Wang | Wei He | Hua Wu | Haiyang Wu | Wei Li | Haifeng Wang | Enhong Chen
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Chinese poetry generation is a very challenging task in natural language processing. In this paper, we propose a novel two-stage poetry generating method which first plans the sub-topics of the poem according to the user’s writing intent, and then generates each line of the poem sequentially, using a modified recurrent neural network encoder-decoder framework. The proposed planning-based method can ensure that the generated poem is coherent and semantically consistent with the user’s intent. A comprehensive evaluation with human judgments demonstrates that our proposed approach outperforms the state-of-the-art poetry generating methods and the poem quality is somehow comparable to human poets.

pdf
Latent Topic Embedding
Di Jiang | Lei Shi | Rongzhong Lian | Hua Wu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Topic modeling and word embedding are two important techniques for deriving latent semantics from data. General-purpose topic models typically work in coarse granularity by capturing word co-occurrence at the document/sentence level. In contrast, word embedding models usually work in much finer granularity by modeling word co-occurrence within small sliding windows. With the aim of deriving latent semantics by considering word co-occurrence at different levels of granularity, we propose a novel model named Latent Topic Embedding (LTE), which seamlessly integrates topic generation and embedding learning in one unified framework. We further propose an efficient Monte Carlo EM algorithm to estimate the parameters of interest. By retaining the individual advantages of topic modeling and word embedding, LTE results in better latent topics and word embedding. Extensive experiments verify the superiority of LTE over the state-of-the-arts.

pdf
Active Learning for Dependency Parsing with Partial Annotation
Zhenghua Li | Min Zhang | Yue Zhang | Zhanyi Liu | Wenliang Chen | Hua Wu | Haifeng Wang
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Minimum Risk Training for Neural Machine Translation
Shiqi Shen | Yong Cheng | Zhongjun He | Wei He | Hua Wu | Maosong Sun | Yang Liu
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Semi-Supervised Learning for Neural Machine Translation
Yong Cheng | Wei Xu | Zhongjun He | Wei He | Hua Wu | Maosong Sun | Yang Liu
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2015

pdf
Improved beam search with constrained softmax for NMT
Xiaoguang Hu | Wei Li | Xiang Lan | Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit XV: Papers

pdf
Multi-Task Learning for Multiple Language Translation
Daxiang Dong | Hua Wu | Wei He | Dianhai Yu | Haifeng Wang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf
Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System
Zhuoran Wang | Hongliang Chen | Guanchun Wang | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf
Improve Statistical Machine Translation with Context-Sensitive Bilingual Semantic Embedding Model
Haiyang Wu | Daxiang Dong | Xiaoguang Hu | Dianhai Yu | Wei He | Hua Wu | Haifeng Wang | Ting Liu
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf
Transformation from Discontinuous to Continuous Word Alignment Improves Translation Quality
Zhongjun He | Hua Wu | Haifeng Wang | Ting Liu
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf
Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs
Xiaoning Zhu | Zhongjun He | Hua Wu | Conghui Zhu | Haifeng Wang | Tiejun Zhao
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Kristina Toutanova | Hua Wu
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Kristina Toutanova | Hua Wu
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2013

pdf
Improving Pivot-Based Statistical Machine Translation Using Random Walk
Xiaoning Zhu | Zhongjun He | Hua Wu | Haifeng Wang | Conghui Zhu | Tiejun Zhao
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf
Generalization of Words for Chinese Dependency Parsing
Xianchao Wu | Jie Zhou | Yu Sun | Zhanyi Liu | Dianhai Yu | Hua Wu | Haifeng Wang
Proceedings of the 13th International Conference on Parsing Technologies (IWPT 2013)

2012

pdf
Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information
Jinsong Su | Hua Wu | Haifeng Wang | Yidong Chen | Xiaodong Shi | Huailin Dong | Qun Liu
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Improve SMT Quality with Automatically Extracted Paraphrase Rules
Wei He | Hua Wu | Haifeng Wang | Ting Liu
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2011

pdf
Reordering with Source Language Collocations
Zhanyi Liu | Haifeng Wang | Hua Wu | Ting Liu | Sheng Li
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2010

pdf
Improving Statistical Machine Translation with Monolingual Collocation
Zhanyi Liu | Haifeng Wang | Hua Wu | Sheng Li
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

2009

pdf
Collocation Extraction Using Monolingual Word Alignment Method
Zhanyi Liu | Haifeng Wang | Hua Wu | Sheng Li
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf
Exploiting Heterogeneous Treebanks for Parsing
Zheng-Yu Niu | Haifeng Wang | Hua Wu
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf
Revisiting Pivot Language Approach for Machine Translation
Hua Wu | Haifeng Wang
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

2008

pdf
Domain Adaptation for Statistical Machine Translation with Domain Dictionary and Monolingual Corpora
Hua Wu | Haifeng Wang | Chengqing Zong
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf
The TCH machine translation system for IWSLT 2008.
Haifeng Wang | Hua Wu | Xiaoguang Hu | Zhanyi Liu | Jianfeng Li | Dengjun Ren | Zhengyu Niu
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper reports on the first participation of TCH (Toshiba (China) Research and Development Center) at the IWSLT evaluation campaign. We participated in all the 5 translation tasks with Chinese as source language or target language. For Chinese-English and English-Chinese translation, we used hybrid systems that combine rule-based machine translation (RBMT) method and statistical machine translation (SMT) method. For Chinese-Spanish translation, phrase-based SMT models were used. For the pivot task, we combined the translations generated by a pivot based statistical translation model and a statistical transfer translation model (firstly, translating from Chinese to English, and then from English to Spanish). Moreover, for better performance of MT, we improved each module in the MT systems as follows: adapting Chinese word segmentation to spoken language translation, selecting out-of-domain corpus to build language models, using bilingual dictionaries to correct word alignment results, handling NE translation and selecting translations from the outputs of multiple systems. According to the automatic evaluation results on the full test sets, we top in all the 5 tasks.

2007

pdf
Pivot Language Approach for Phrase-Based Statistical Machine Translation
Hua Wu | Haifeng Wang
Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics

pdf
Log-linear generation models for example-based machine translation
Zhanyi Liu | Hifeng Wang | Hua Wu
Proceedings of Machine Translation Summit XI: Papers

pdf
Improving statistical word alignment with various clues
Dengjun Ren | Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit XI: Papers

pdf
Comparative study of word alignment heuristics and phrase-based SMT
Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit XI: Papers

pdf
Using RBMT Systems to Produce Bilingual Corpus for SMT
Xiaoguang Hu | Haifeng Wang | Hua Wu
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

2006

pdf
Word Alignment for Languages with Scarce Resources Using Bilingual Corpora of Other Language Pairs
Haifeng Wang | Hua Wu | Zhanyi Liu
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

pdf
Boosting Statistical Word Alignment Using Labeled and Unlabeled Data
Hua Wu | Haifeng Wang | Zhanyi Liu
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

2005

pdf
Improving Statistical Word Alignment with Ensemble Methods
Hua Wu | Haifeng Wang
Second International Joint Conference on Natural Language Processing: Full Papers

pdf
Example-based Machine Translation Based on TSC and Statistical Generation
Zhanyi Liu | Haifeng Wang | Hua Wu
Proceedings of Machine Translation Summit X: Papers

This paper proposes a novel Example-Based Machine Translation (EBMT) method based on Tree String Correspondence (TSC) and statistical generation. In this method, the translation examples are represented as TSC, which consists of three parts: a parse tree in the source language, a string in the target language, and the correspondences between the leaf nodes of the source language tree and the substrings of the target language string. During the translation, the input sentence is first parsed into a tree. Then the TSC forest is searched out if it is best matched with the parse tree. The translation is generated by using a statistical generation model to combine the target language strings in the TSCs. The generation model consists of three parts: the semantic similarity between words, the word translation probability, and the target language model. Based on the above method, we build an English-to-Chinese Machine Translation (ECMT) system. Experimental results indicate that the performance of our system is comparable with that of the state-of-the-art commercial ECMT systems.

pdf
Boosting Statistical Word Alignment
Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit X: Papers

This paper proposes an approach to improve statistical word alignment with the boosting method. Applying boosting to word alignment must solve two problems. The first is how to build the reference set for the training data. We propose an approach to automatically build a pseudo reference set, which can avoid manual annotation of the training set. The second is how to calculate the error rate of each individual word aligner. We solve this by calculating the error rate of a manually annotated held-out data set instead of the entire training set. In addition, the final ensemble takes into account the weights of the alignment links produced by the individual word aligners. Experimental results indicate that the boosting method proposed in this paper performs much better than the original word aligner, achieving a large error rate reduction.

pdf
Improving Translation Memory with Word Alignment Information
Hua Wu | Haifeng Wang | Zhanyi Liu | Kai Tang
Proceedings of Machine Translation Summit X: Posters

This paper describes a generalized translation memory system, which takes advantage of sentence level matching, sub-sentential matching, and pattern-based machine translation technologies. All of the three techniques generate translation suggestions with the assistance of word alignment information. For the sentence level matching, the system generates the translation suggestion by modifying the translations of the most similar example with word alignment information. For sub-sentential matching, the system locates the translation fragments in several examples with word alignment information, and then generates the translation suggestion by combining these translation fragments. For pattern-based machine translation, the system first extracts translation patterns from examples using word alignment information and then generates translation suggestions with pattern matching. This system is compared with a traditional translation memory system without word alignment information in terms of translation efficiency and quality. Evaluation results indicate that our system improves the translation quality and saves about 20% translation time.

pdf
Alignment Model Adaptation for Domain-Specific Word Alignment
Hua Wu | Haifeng Wang | Zhanyi Liu
Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05)

2004

pdf bib
Improving Domain-Specific Word Alignment for Computer Assisted Translation
Hua Wu | Haifeng Wang
Proceedings of the ACL Interactive Poster and Demonstration Sessions

pdf
Improving Statistical Word Alignment with a Rule-Based Machine Translation System
Hua Wu | Haifeng Wang
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

pdf
Improving domain-specific word alignment with a general bilingual corpus
Hua Wu | Haifeng Wang
Proceedings of the 6th Conference of the Association for Machine Translation in the Americas: Technical Papers

In conventional word alignment methods, some employ statistical models or statistical measures, which need large-scale bilingual sentence-aligned training corpora. Others employ dictionaries to guide alignment selection. However, these methods achieve unsatisfactory alignment results when performing word alignment on a small-scale domain-specific bilingual corpus without terminological lexicons. This paper proposes an approach to improve word alignment in a specific domain, in which only a small-scale domain-specific corpus is available, by adapting the word alignment information in the general domain to the specific domain. This approach first trains two statistical word alignment models with the large-scale corpus in the general domain and the small-scale corpus in the specific domain respectively, and then improves the domain-specific word alignment with these two models. Experimental results show a significant improvement in terms of both alignment precision and recall, achieving a relative error rate reduction of 21.96% as compared with state-of-the-art technologies.

2003

pdf
Synonymous Collocation Extraction Using Translation Information
Hua Wu | Ming Zhou
Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics

pdf
Optimizing Synonym Extraction Using Monolingual and Bilingual Resources
Hua Wu | Ming Zhou
Proceedings of the Second International Workshop on Paraphrasing

2000

pdf
Chinese Generation in a Spoken Dialogue Translation System
Hua Wu | Taiyi Huang | Chengqing Zong
COLING 2000 Volume 2: The 18th International Conference on Computational Linguistics

Search
Co-authors