Furu Wei


2023

pdf
SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
Liang Wang | Nan Yang | Xiaolong Huang | Binxing Jiao | Linjun Yang | Daxin Jiang | Rangan Majumder | Furu Wei
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we propose SimLM (Similarity matching with Language Model pre-training), a simple yet effective pre-training method for dense passage retrieval. It employs a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training. We use a replaced language modeling objective, which is inspired by ELECTRA (Clark et al., 2020), to improve the sample efficiency and reduce the mismatch of the input distribution between pre-training and fine-tuning. SimLM only requires access to an unlabeled corpus and is more broadly applicable when there are no labeled data or queries. We conduct experiments on several large-scale passage retrieval datasets and show substantial improvements over strong baselines under various settings. Remarkably, SimLM even outperforms multi-vector approaches such as ColBERTv2 (Santhanam et al., 2021) which incurs significantly more storage cost. Our code and model checkpoints are available at https://github.com/microsoft/unilm/tree/master/simlm .

pdf
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Ziheng Li | Shaohan Huang | Zihan Zhang | Zhi-Hong Deng | Qiang Lou | Haizhen Huang | Jian Jiao | Furu Wei | Weiwei Deng | Qi Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. However, our research indicates that token-level alignment is also crucial in multilingual scenarios, which has not been fully explored previously. Based on our findings, we propose a dual-alignment pre-training (DAP) framework for cross-lingual sentence embedding that incorporates both sentence-level and token-level alignment. To achieve this, we introduce a novel representation translation learning (RTL) task, where the model learns to use one-side contextualized token representation to reconstruct its translation counterpart. This reconstruction objective encourages the model to embed translation information into the token representation. Compared to other token-level alignment methods such as translation language modeling, RTL is more suitable for dual encoder architectures and is computationally efficient. Extensive experiments on three sentence-level cross-lingual benchmarks demonstrate that our approach can significantly improve sentence embedding. Our code is available at https://github.com/ChillingDream/DAP.

pdf
Pre-Training to Learn in Context
Yuxian Gu | Li Dong | Furu Wei | Minlie Huang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community. However, the ability of in-context learning is not fully exploited because language models are not explicitly trained to learn in context. To this end, we propose PICL (Pre-training for In-Context Learning), a framework to enhance the language models’ in-context learning ability by pre-training the model on a large collection of “intrinsic tasks” in the general plain-text corpus using the simple language modeling objective. PICL encourages the model to infer and perform tasks by conditioning on the contexts while maintaining task generalization of pre-trained models. We evaluate the in-context learning performance of the model trained with PICL on seven widely-used text classification datasets and the Super-NaturalInstrctions benchmark, which contains 100+ NLP tasks formulated to text generation. Our experiments show that PICL is more effective and task-generalizable than a range of baselines, outperforming larger language models with nearly 4x parameters. The code is publicly available at https://github.com/thu-coai/PICL.

pdf
Multiview Identifiers Enhanced Generative Retrieval
Yongqi Li | Nan Yang | Liang Wang | Furu Wei | Wenjie Li
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Instead of simply matching a query to pre-existing passages, generative retrieval generates identifier strings of passages as the retrieval target. At a cost, the identifier must be distinctive enough to represent a passage. Current approaches use either a numeric ID or a text piece (such as a title or substrings) as the identifier. However, these identifiers cannot cover a passage’s content well. As such, we are motivated to propose a new type of identifier, synthetic identifiers, that are generated based on the content of a passage and could integrate contextualized information that text pieces lack. Furthermore, we simultaneously consider multiview identifiers, including synthetic identifiers, titles, and substrings. These views of identifiers complement each other and facilitate the holistic ranking of passages from multiple perspectives. We conduct a series of experiments on three public datasets, and the results indicate that our proposed approach performs the best in generative retrieval, demonstrating its effectiveness and robustness.

pdf
GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator
Jian Yang | Shuming Ma | Li Dong | Shaohan Huang | Haoyang Huang | Yuwei Yin | Dongdong Zhang | Liqun Yang | Furu Wei | Zhoujun Li
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Pre-trained models have achieved remarkable success in natural language processing (NLP). However, existing pre-training methods underutilize the benefits of language understanding for generation. Inspired by the idea of Generative Adversarial Networks (GANs), we propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator, unifying the ability of language understanding and generation in a single model. Our model, named as GanLM, is trained with two pre-training objectives: replaced token detection and replaced token denoising. Specifically, given masked source sentences, the generator outputs the target distribution and the discriminator predicts whether the target sampled tokens from distribution are incorrect. The target sentence is replaced with misclassified tokens to construct noisy previous context, which is used to generate the gold sentence. In general, both tasks improve the ability of language understanding and generation by selectively using the denoising data. Extensive experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models (PLMs) and achieves state-of-the-art performance.

pdf
A Length-Extrapolatable Transformer
Yutao Sun | Li Dong | Barun Patra | Shuming Ma | Shaohan Huang | Alon Benhaim | Vishrav Chaudhary | Xia Song | Furu Wei
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Position modeling plays a critical role in Transformers. In this paper, we focus on length extrapolation, i.e., training on short texts while evaluating longer sequences. We define attention resolution as an indicator of extrapolation. Then we propose two designs to improve the above metric of Transformers. Specifically, we introduce a relative position embedding to explicitly maximize attention resolution. Moreover, we use blockwise causal attention during inference for better resolution. We evaluate different Transformer variants with language modeling. Experimental results show that our model achieves strong performance in both interpolation and extrapolation settings. The code will be available at https://aka.ms/LeX-Transformer.

pdf
Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning
Barun Patra | Saksham Singhal | Shaohan Huang | Zewen Chi | Li Dong | Furu Wei | Vishrav Chaudhary | Xia Song
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we elaborate upon recipes for building multilingual representation models that are not only competitive with existing state-of-the-art models but are also more parameter efficient, thereby promoting better adoption in resource-constrained scenarios and practical applications. We show that going beyond English-centric bitexts, coupled with a novel sampling strategy aimed at reducing under-utilization of training data, substantially boosts performance across model sizes for both Electra and MLM pre-training objectives. We introduce XY-LENT: X-Y bitext enhanced Language ENcodings using Transformers which not only achieves state-of-the-art performance over 5 cross-lingual tasks within all model size bands, is also competitive across bands. Our XY-LENT XL variant outperforms XLM-R XXL and exhibits competitive performance with mT5 XXL while being 5x and 6x smaller respectively. We then show that our proposed method helps ameliorate the curse of multilinguality, with the XY-LENT XL achieving 99.3% GLUE performance and 98.5% SQuAD 2.0 performance compared to a SoTA English only model in the same size band. We then analyze our models performance on extremely low resource languages and posit that scaling alone may not be sufficient for improving the performance in this scenario

pdf
Pre-training Language Model as a Multi-perspective Course Learner
Beiduo Chen | Shaohan Huang | Zihan Zhang | Wu Guo | Zhenhua Ling | Haizhen Huang | Furu Wei | Weiwei Deng | Qi Zhang
Findings of the Association for Computational Linguistics: ACL 2023

ELECTRA, the generator-discriminator pre-training framework, has achieved impressive semantic construction capability among various downstream tasks. Despite the convincing performance, ELECTRA still faces the challenges of monotonous training and deficient interaction. Generator with only masked language modeling (MLM) leads to biased learning and label imbalance for discriminator, decreasing learning efficiency; no explicit feedback loop from discriminator to generator results in the chasm between these two components, underutilizing the course learning. In this study, a multi-perspective course learning (MCL) method is proposed to fetch a many degrees and visual angles for sample-efficient pre-training, and to fully leverage the relationship between generator and discriminator. Concretely, three self-supervision courses are designed to alleviate inherent flaws of MLM and balance the label in a multi-perspective way. Besides, two self-correction courses are proposed to bridge the chasm between the two encoders by creating a “correction notebook” for secondary-supervision. Moreover, a course soups trial is conducted to solve the “tug-of-war” dynamics problem of MCL, evolving a stronger pre-trained model. Experimental results show that our method significantly improves ELECTRA’s average performance by 2.8% and 3.2% absolute points respectively on GLUE and SQuAD 2.0 benchmarks, and overshadows recent advanced ELECTRA-style models under the same settings. The pre-trained MCL model is available at https://huggingface.co/McmanusChen/MCL-base.

pdf
Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers
Damai Dai | Yutao Sun | Li Dong | Yaru Hao | Shuming Ma | Zhifang Sui | Furu Wei
Findings of the Association for Computational Linguistics: ACL 2023

Large pretrained language models have shown surprising in-context learning (ICL) ability. With a few demonstration input-label pairs, they can predict the label for an unseen input without parameter updates. Despite the great success in performance, its working mechanism still remains an open question. In this paper, we explain language models as meta-optimizers and understand in-context learning as implicit finetuning. Theoretically, we figure out that Transformer attention has a dual form of gradient descent. On top of it, we understand ICL as follows: GPT first produces meta-gradients according to the demonstration examples, and then these meta-gradients are applied to the original GPT to build an ICL model. We comprehensively compare the behaviors of in-context learning and explicit finetuning on real tasks to provide empirical evidence that supports our understanding. Experimental results show that in-context learning behaves similarly to explicit finetuning from multiple perspectives. Inspired by the dual form between Transformer attention and gradient descent, we design a momentum-based attention by analogy with gradient descent with momentum. The improved performance over vanilla attention further supports our understanding from another perspective, and more importantly, shows the potential to utilize our understanding for future model design. The code is available at https://aka.ms/icl.

pdf
On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation
Liang Chen | Shuming Ma | Dongdong Zhang | Furu Wei | Baobao Chang
Findings of the Association for Computational Linguistics: ACL 2023

While multilingual neural machine translation has achieved great success, it suffers from the off-target issue, where the translation is in the wrong language. This problem is more pronounced on zero-shot translation tasks. In this work, we find that failing in encoding discriminative target language signal will lead to off-target and a closer lexical distance (i.e., KL-divergence) between two languages’ vocabularies is related with a higher off-target rate. We also find that solely isolating the vocab of different languages in the decoder can alleviate the problem. Motivated by the findings, we propose Language Aware Vocabulary Sharing (LAVS), a simple and effective algorithm to construct the multilingual vocabulary, that greatly alleviates the off-target problem of the translation model by increasing the KL-divergence between languages. We conduct experiments on a multilingual machine translation benchmark in 11 languages. Experiments show that the off-target rate for 90 translation tasks is reduced from 29% to 8%, while the overall BLEU score is improved by an average of 1.9 points without extra training cost or sacrificing the supervised directions’ performance. We release the code at https://github.com/PKUnlp-icler/Off-Target-MNMThttps://github.com/PKUnlp-icler/Off-Target-MNMT for reproduction.

2022

pdf
Controllable Natural Language Generation with Contrastive Prefixes
Jing Qian | Li Dong | Yelong Shen | Furu Wei | Weizhu Chen
Findings of the Association for Computational Linguistics: ACL 2022

To guide the generation of large pretrained language models (LM), previous work has focused on directly fine-tuning the language model or utilizing an attribute discriminator. In this work, we propose a novel lightweight framework for controllable GPT2 generation, which utilizes a set of small attribute-specific vectors, called prefixes (Li and Liang, 2021), to steer natural language generation. Different from Li and Liang (2021), where each prefix is trained independently, we take the relationship among prefixes into consideration and train multiple prefixes simultaneously. We propose a novel supervised method and also an unsupervised method to train the prefixes for single-aspect control while the combination of these two methods can achieve multi-aspect control. Experimental results on both single-aspect and multi-aspect control show that our methods can guide generation towards the desired attributes while keeping high linguistic quality.

pdf
XFUND: A Benchmark Dataset for Multilingual Visually Rich Form Understanding
Yiheng Xu | Tengchao Lv | Lei Cui | Guoxin Wang | Yijuan Lu | Dinei Florencio | Cha Zhang | Furu Wei
Findings of the Association for Computational Linguistics: ACL 2022

Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. However, the existed research work has focused only on the English domain while neglecting the importance of multilingual generalization. In this paper, we introduce a human-annotated multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chinese, Japanese, Spanish, French, Italian, German, Portuguese). Meanwhile, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually rich document understanding. Experimental results show that the LayoutXLM model has significantly outperformed the existing SOTA cross-lingual pre-trained models on the XFUND dataset. The XFUND dataset and the pre-trained LayoutXLM model have been publicly available at https://aka.ms/layoutxlm.

pdf
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption
Tianyu Chen | Hangbo Bao | Shaohan Huang | Li Dong | Binxing Jiao | Daxin Jiang | Haoyi Zhou | Jianxin Li | Furu Wei
Findings of the Association for Computational Linguistics: ACL 2022

As more and more pre-trained language models adopt on-cloud deployment, the privacy issues grow quickly, mainly for the exposure of plain-text user data (e.g., search history, medical record, bank account). Privacy-preserving inference of transformer models is on the demand of cloud service users. To protect privacy, it is an attractive choice to compute only with ciphertext in homomorphic encryption (HE). However, enabling pre-trained models inference on ciphertext data is difficult due to the complex computations in transformer blocks, which are not supported by current HE tools yet. In this work, we introduce THE-X, an approximation approach for transformers, which enables privacy-preserving inference of pre-trained models developed by popular frameworks. THE-X proposes a workflow to deal with complex computation in transformer networks, including all the non-polynomial functions like GELU, softmax, and LayerNorm. Experiments reveal our proposed THE-X can enable transformer inference on encrypted data for different downstream tasks, all with negligible performance drop but enjoying the theory-guaranteed privacy-preserving advantage.

pdf
CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation
Jian Yang | Shaohan Huang | Shuming Ma | Yuwei Yin | Li Dong | Dongdong Zhang | Hongcheng Guo | Zhoujun Li | Furu Wei
Findings of the Association for Computational Linguistics: EMNLP 2022

Named entity recognition (NER) suffers from the scarcity of annotated training data, especially for low-resource languages without labeled data. Cross-lingual NER has been proposed to alleviate this issue by transferring knowledge from high-resource languages to low-resource languages via aligned cross-lingual representations or machine translation results. However, the performance of cross-lingual NER methods is severely affected by the unsatisfactory quality of translation or label projection. To address these problems, we propose a Cross-lingual Entity Projection framework (CROP) to enable zero-shot cross-lingual NER with the help of a multilingual labeled sequence translation model. Specifically, the target sequence is first translated into the source language and then tagged by a source NER model. We further adopt a labeled sequence translation model to project the tagged sequence back to the target language and label the target raw sentence. Ultimately, the whole pipeline is integrated into an end-to-end model by the way of self-training. Experimental results on two benchmarks demonstrate that our method substantially outperforms the previous strong baseline by a large margin of +3 7 F1 scores and achieves state-of-the-art performance.

pdf
XDoc: Unified Pre-training for Cross-Format Document Understanding
Jingye Chen | Tengchao Lv | Lei Cui | Cha Zhang | Furu Wei
Findings of the Association for Computational Linguistics: EMNLP 2022

The surge of pre-training has witnessed the rapid development of document understanding recently. Pre-training and fine-tuning framework has been effectively used to tackle texts in various formats, including plain texts, document texts, and web texts. Despite achieving promising performance, existing pre-trained models usually target one specific document format at one time, making it difficult to combine knowledge from multiple document formats. To address this, we propose XDoc, a unified pre-trained model which deals with different document formats in a single model. For parameter efficiency, we share backbone parameters for different formats such as the word embedding layer and the Transformer layers. Meanwhile, we introduce adaptive layers with lightweight parameters to enhance the distinction across different formats. Experimental results have demonstrated that with only 36.7% parameters, XDoc achieves comparable or even better performance on a variety of downstream tasks compared with the individual pre-trained models, which is cost effective for real-world deployment. The code and pre-trained models are publicly available at https://aka.ms/xdoc.

pdf
Snapshot-Guided Domain Adaptation for ELECTRA
Daixuan Cheng | Shaohan Huang | Jianfeng Liu | Yuefeng Zhan | Hao Sun | Furu Wei | Denvy Deng | Qi Zhang
Findings of the Association for Computational Linguistics: EMNLP 2022

Discriminative pre-trained language models, such as ELECTRA, have achieved promising performances in a variety of general tasks. However, these generic pre-trained models struggle to capture domain-specific knowledge of domain-related tasks. In this work, we propose a novel domain-adaptation method for ELECTRA, which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters. We show that by re-weighting the losses of domain-specific tokens, ELECTRA can be effectively adapted to different domains. The experimental results in both computer science and biomedical domains show that the proposed method can achieve state-of-the-art results on the domain-related tasks.

pdf
Attention Temperature Matters in Abstractive Summarization Distillation
Shengqiang Zhang | Xingxing Zhang | Hangbo Bao | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent progress of abstractive text summarization largely relies on large pre-trained sequence-to-sequence Transformer models, which are computationally expensive. This paper aims to distill these large models into smaller ones for faster inference and with minimal performance loss. Pseudo-labeling based methods are popular in sequence-to-sequence model distillation. In this paper, we find simply manipulating attention temperatures in Transformers can make pseudo labels easier to learn for student models. Our experiments on three summarization datasets show our proposed method consistently improves vanilla pseudo-labeling based methods. Further empirical analysis shows that both pseudo labels and summaries produced by our students are shorter and more abstractive.

pdf
Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation
Guanhua Chen | Shuming Ma | Yun Chen | Dongdong Zhang | Jia Pan | Wenping Wang | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source languages unseen during supervised training. Following this idea, we present SixT+, a strong many-to-English NMT model that supports 100 source languages but is trained with a parallel dataset in only six source languages. SixT+ initializes the decoder embedding and the full encoder with XLM-R large and then trains the encoder and decoder layers with a simple two-stage training strategy. SixT+ achieves impressive performance on many-to-English translation. It significantly outperforms CRISS and m2m-100, two strong multilingual NMT systems, with an average gain of 7.2 and 5.0 BLEU respectively. Additionally, SixT+ offers a set of model parameters that can be further fine-tuned to other unsupervised tasks. We demonstrate that adding SixT+ initialization outperforms state-of-the-art explicitly designed unsupervised NMT models on Si<->En and Ne<->En by over 1.2 average BLEU. When applied to zero-shot cross-lingual abstractive summarization, it produces an average performance gain of 12.3 ROUGE-L over mBART-ft. We conduct detailed analyses to understand the key ingredients of SixT+, including multilinguality of the auxiliary parallel data, positional disentangled encoder, and the cross-lingual transferability of its encoder.

pdf
Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization
Ruipeng Jia | Xingxing Zhang | Yanan Cao | Zheng Lin | Shi Wang | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages. Given English gold summaries and documents, sentence-level labels for extractive summarization are usually generated using heuristics. However, these monolingual labels created on English datasets may not be optimal on datasets of other languages, for that there is the syntactic or semantic discrepancy between different languages. In this way, it is possible to translate the English dataset to other languages and obtain different sets of labels again using heuristics. To fully leverage the information of these different sets of labels, we propose NLSSum (Neural Label Search for Summarization), which jointly learns hierarchical weights for these different sets of labels together with our summarization model. We conduct multilingual zero-shot summarization experiments on MLSUM and WikiLingua datasets, and we achieve state-of-the-art results using both human and automatic evaluations across these two datasets.

pdf
SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
Junyi Ao | Rui Wang | Long Zhou | Chengyi Wang | Shuo Ren | Yu Wu | Shujie Liu | Tom Ko | Qing Li | Yu Zhang | Zhihua Wei | Yao Qian | Jinyu Li | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder. Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder. Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification.

pdf
MarkupLM: Pre-training of Text and Markup Language for Visually Rich Document Understanding
Junlong Li | Yiheng Xu | Lei Cui | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Multimodal pre-training with text, layout, and image has made significant progress for Visually Rich Document Understanding (VRDU), especially the fixed-layout documents such as scanned document images. While, there are still a large number of digital documents where the layout information is not fixed and needs to be interactively and dynamically rendered for visualization, making existing layout-based pre-training approaches not easy to apply. In this paper, we propose MarkupLM for document understanding tasks with markup languages as the backbone, such as HTML/XML-based documents, where text and markup information is jointly pre-trained. Experiment results show that the pre-trained MarkupLM significantly outperforms the existing strong baseline models on several document understanding tasks. The pre-trained model and code will be publicly available at https://aka.ms/markuplm.

pdf
CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment
Haoyu Song | Li Dong | Weinan Zhang | Ting Liu | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption pairs, CLIP itself should also have acquired some few-shot abilities for vision-language tasks. In this work, we empirically show that CLIP can be a strong vision-language few-shot learner by leveraging the power of language. We first evaluate CLIP’s zero-shot performance on a typical visual question answering task and demonstrate a zero-shot cross-modality transfer capability of CLIP on the visual entailment task. Then we propose a parameter-efficient fine-tuning strategy to boost the few-shot performance on the vqa task. We achieve competitive zero/few-shot results on the visual question answering and visual entailment tasks without introducing any additional pre-training procedure.

pdf
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
Zewen Chi | Shaohan Huang | Li Dong | Shuming Ma | Bo Zheng | Saksham Singhal | Payal Bajaj | Xia Song | Xian-Ling Mao | Heyan Huang | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides, we pretrain the model, named as XLM-E, on both multilingual and parallel corpora. Our model outperforms the baseline models on various cross-lingual understanding tasks with much less computation cost. Moreover, analysis shows that XLM-E tends to obtain better cross-lingual transferability.

pdf
StableMoE: Stable Routing Strategy for Mixture of Experts
Damai Dai | Li Dong | Shuming Ma | Bo Zheng | Zhifang Sui | Baobao Chang | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i.e., the target expert of the same input may change along with training, but only one expert will be activated for the input during inference. The routing fluctuation tends to harm sample efficiency because the same input updates different experts but only one is finally used. In this paper, we propose StableMoE with two training stages to address the routing fluctuation problem. In the first training stage, we learn a balanced and cohesive routing strategy and distill it into a lightweight router decoupled from the backbone model. In the second training stage, we utilize the distilled router to determine the token-to-expert assignment and freeze it for a stable routing strategy. We validate our method on language modeling and multilingual machine translation. The results show that StableMoE outperforms existing MoE methods in terms of both convergence speed and performance.

pdf
Knowledge Neurons in Pretrained Transformers
Damai Dai | Li Dong | Yaru Hao | Zhifang Sui | Baobao Chang | Furu Wei
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Large-scale pretrained language models are surprisingly good at recalling factual knowledge presented in the training corpus. In this paper, we present preliminary studies on how factual knowledge is stored in pretrained Transformers by introducing the concept of knowledge neurons. Specifically, we examine the fill-in-the-blank cloze task for BERT. Given a relational fact, we propose a knowledge attribution method to identify the neurons that express the fact. We find that the activation of such knowledge neurons is positively correlated to the expression of their corresponding facts. In our case studies, we attempt to leverage knowledge neurons to edit (such as update, and erase) specific factual knowledge without fine-tuning. Our results shed light on understanding the storage of knowledge within pretrained Transformers.

pdf
SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training
Ziqiang Zhang | Long Zhou | Junyi Ao | Shujie Liu | Lirong Dai | Jinyu Li | Furu Wei
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

The rapid development of single-modal pre-training has prompted researchers to pay more attention to cross-modal pre-training methods. In this paper, we propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a shared unit encoder. Leveraging hidden-unit as an interface to align speech and text, we can decompose the speech-to-text model into a speech-to-unit model and a unit-to-text model, which can be jointly pre-trained with unpaired speech and text data respectively. Our proposed SpeechUT is fine-tuned and evaluated on automatic speech recognition (ASR) and speech translation (ST) tasks. Experimental results show that SpeechUT gets substantial improvements over strong baselines, and achieves state-of-the-art performance on both the LibriSpeech ASR and MuST-C ST tasks. To better understand the proposed SpeechUT, detailed analyses are conducted. The code and pre-trained models are available at https://aka.ms/SpeechUT.

pdf
PromptBERT: Improving BERT Sentence Embeddings with Prompts
Ting Jiang | Jian Jiao | Shaohan Huang | Zihan Zhang | Deqing Wang | Fuzhen Zhuang | Furu Wei | Haizhen Huang | Denvy Deng | Qi Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analysis the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token embedding bias and ineffective BERT layers. Then we propose the first prompt-based sentence embeddings method and discuss two prompt representing methods and three prompt searching methods to make BERT achieve better sentence embeddings .Moreover, we propose a novel unsupervised training objective by the technology of template denoising, which substantially shortens the performance gap between the supervised and unsupervised settings. Extensive experiments show the effectiveness of our method. Compared to SimCSE, PromptBert achieves 2.29 and 2.58 points of improvement based on BERT and RoBERTa in the unsupervised setting.

pdf
Distilled Dual-Encoder Model for Vision-Language Understanding
Zekun Wang | Wenhui Wang | Haichao Zhu | Ming Liu | Bing Qin | Furu Wei
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

On vision-language understanding (VLU) tasks, fusion-encoder vision-language models achieve superior results but sacrifice efficiency because of the simultaneous encoding of images and text. On the contrary, the dual encoder model that separately encodes images and text has the advantage in efficiency, while failing on VLU tasks due to the lack of deep cross-modal interactions. To get the best of both worlds, we propose DiDE, a framework that distills the knowledge of the fusion-encoder teacher model into the dual-encoder student model. Since the cross-modal interaction is the key to the superior performance of teacher model but is absent in the student model, we encourage the student not only to mimic the predictions of teacher, but also to calculate the cross-modal attention distributions and align with the teacher. Experimental results demonstrate that DiDE is competitive with the fusion-encoder teacher model in performance (only a 1% drop) while enjoying 4 times faster inference. Further analyses reveal that the proposed cross-modal attention distillation is crucial to the success of our framework.

pdf
EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation
Tao Ge | Si-Qing Chen | Furu Wei
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

We introduce EdgeFormer – a parameter-efficient Transformer for on-device seq2seq generation under the strict computation and memory constraints. Compared with the previous parameter-efficient Transformers, EdgeFormer applies two novel principles for cost-effective parameterization, allowing it to perform better given the same parameter budget; moreover, EdgeFormer is further enhanced by layer adaptation innovation that is proposed for improving the network with shared layers.Extensive experiments show EdgeFormer can effectively outperform previous parameter-efficient Transformer baselines and achieve competitive results under both the computation and memory constraints. Given the promising results, we release EdgeLM – the pretrained version of EdgeFormer, which is the first publicly available pretrained on-device seq2seq model that can be easily fine-tuned for seq2seq tasks with strong results, facilitating on-device seq2seq generation in practice.

pdf
Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt
Lianzhe Huang | Shuming Ma | Dongdong Zhang | Furu Wei | Houfeng Wang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Prompt-based tuning has been proven effective for pretrained language models (PLMs). While most of the existing work focuses on the monolingual prompts, we study the multilingual prompts for multilingual PLMs, especially in the zero-shot cross-lingual setting. To alleviate the effort of designing different prompts for multiple languages, we propose a novel model that uses a unified prompt for all languages, called UniPrompt. Different from the discrete prompts and soft prompts, the unified prompt is model-based and language-agnostic. Specifically, the unified prompt is initialized by a multilingual PLM to produce language-independent representation, after which is fused with the text input. During inference, the prompts can be pre-computed so that no extra computation cost is needed. To collocate with the unified prompt, we propose a new initialization method for the target label word to further improve the model’s transferability across languages. Extensive experiments show that our proposed methods can significantly outperform the strong baselines across different languages. We release data and code to facilitate future research.

pdf
Plug and Play Knowledge Distillation for kNN-LM with External Logits
Xuyang Jin | Tao Ge | Furu Wei
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Despite the promising evaluation results by knowledge distillation (KD) in natural language understanding (NLU) and sequence-to-sequence (seq2seq) tasks, KD for causal language modeling (LM) remains a challenge. In this paper, we present a novel perspective of knowledge distillation by proposing plug and play knowledge distillation (PP-KD) to improve a (student) kNN-LM that is the state-of-the-art in causal language modeling by leveraging external logits from either a powerful or a heterogeneous (teacher) LM. Unlike conventional logit-based KD where the teacher’s knowledge is built-in during training, PP-KD is plug and play: it stores the teacher’s knowledge (i.e., logits) externally and uses the teacher’s logits of the retrieved k-nearest neighbors during kNN-LM inference at test time. In contrast to marginal perplexity improvement by logit-based KD in conventional neural (causal) LM, PP-KD achieves a significant improvement, enhancing the kNN-LMs in multiple language modeling datasets, showing a novel and promising perspective for causal LM distillation.

2021

pdf
Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains
Yunzhi Yao | Shaohan Huang | Wenhui Wang | Li Dong | Furu Wei
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Grammar-Based Patches Generation for Automated Program Repair
Yu Tang | Long Zhou | Ambrosio Blanco | Shujie Liu | Furu Wei | Ming Zhou | Muyun Yang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers
Wenhui Wang | Hangbo Bao | Shaohan Huang | Li Dong | Furu Wei
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Memory-Efficient Differentiable Transformer Architecture Search
Yuekai Zhao | Li Dong | Yelong Shen | Zhihua Zhang | Furu Wei | Weizhu Chen
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Learning to Sample Replacements for ELECTRA Pre-Training
Yaru Hao | Li Dong | Hangbo Bao | Ke Xu | Furu Wei
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Pseudo-Label Guided Unsupervised Domain Adaptation of Contextual Embeddings
Tianyu Chen | Shaohan Huang | Furu Wei | Jianxin Li
Proceedings of the Second Workshop on Domain Adaptation for NLP

Contextual embedding models such as BERT can be easily fine-tuned on labeled samples to create a state-of-the-art model for many downstream tasks. However, the fine-tuned BERT model suffers considerably from unlabeled data when applied to a different domain. In unsupervised domain adaptation, we aim to train a model that works well on a target domain when provided with labeled source samples and unlabeled target samples. In this paper, we propose a pseudo-label guided method for unsupervised domain adaptation. Two models are fine-tuned on labeled source samples as pseudo labeling models. To learn representations for the target domain, one of those models is adapted by masked language modeling from the target domain. Then those models are used to assign pseudo-labels to target samples. We train the final model with those samples. We evaluate our method on named entity segmentation and sentiment analysis tasks. These experiments show that our approach outperforms baseline methods.

pdf bib
Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders
Guanhua Chen | Shuming Ma | Yun Chen | Li Dong | Dongdong Zhang | Jia Pan | Wenping Wang | Furu Wei
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is under-explored that whether the MPE can help to facilitate the cross-lingual transferability of NMT model. In this paper, we focus on a zero-shot cross-lingual transfer task in NMT. In this task, the NMT model is trained with parallel dataset of only one language pair and an off-the-shelf MPE, then it is directly tested on zero-shot language pairs. We propose SixT, a simple yet effective model for this task. SixT leverages the MPE with a two-stage training schedule and gets further improvement with a position disentangled encoder and a capacity-enhanced decoder. Using this method, SixT significantly outperforms mBART, a pretrained multilingual encoder-decoder model explicitly designed for NMT, with an average improvement of 7.1 BLEU on zero-shot any-to-English test sets across 14 source languages. Furthermore, with much less training computation cost and training data, our model achieves better performance on 15 any-to-English test sets than CRISS and m2m-100, two strong multilingual NMT baselines.

pdf
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
Wangchunshu Zhou | Tao Ge | Canwen Xu | Ke Xu | Furu Wei
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In this paper, we propose Sequence Span Rewriting (SSR), a self-supervised task for sequence-to-sequence (Seq2Seq) pre-training. SSR learns to refine the machine-generated imperfect text spans into ground truth text. SSR provides more fine-grained and informative supervision in addition to the original text-infilling objective. Compared to the prevalent text infilling objectives for Seq2Seq pre-training, SSR is naturally more consistent with many downstream generation tasks that require sentence rewriting (e.g., text summarization, question generation, grammatical error correction, and paraphrase generation). We conduct extensive experiments by using SSR to improve the typical Seq2Seq pre-trained model T5 in a continual pre-training setting and show substantial improvements over T5 on various natural language generation tasks.

pdf
mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs
Zewen Chi | Li Dong | Shuming Ma | Shaohan Huang | Saksham Singhal | Xian-Ling Mao | Heyan Huang | Xia Song | Furu Wei
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Multilingual T5 pretrains a sequence-to-sequence model on massive monolingual texts, which has shown promising results on many cross-lingual tasks. In this paper, we improve multilingual text-to-text transfer Transformer with translation pairs (mT6). Specifically, we explore three cross-lingual text-to-text pre-training tasks, namely, machine translation, translation pair span corruption, and translation span corruption. In addition, we propose a partially non-autoregressive objective for text-to-text pre-training. We evaluate the methods on seven multilingual benchmark datasets, including sentence classification, named entity recognition, question answering, and abstractive summarization. Experimental results show that the proposed mT6 improves cross-lingual transferability over mT5.

pdf
Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training
Bo Zheng | Li Dong | Shaohan Huang | Saksham Singhal | Wanxiang Che | Ting Liu | Xia Song | Furu Wei
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity. To this end, we propose an algorithm VoCap to determine the desired vocabulary capacity of each language. However, increasing the vocabulary size significantly slows down the pre-training speed. In order to address the issues, we propose k-NN-based target sampling to accelerate the expensive softmax. Our experiments show that the multilingual vocabulary learned with VoCap benefits cross-lingual language model pre-training. Moreover, k-NN-based target sampling mitigates the side-effects of increasing the vocabulary size while achieving comparable performance and faster pre-training speed. The code and the pretrained multilingual vocabularies are available at https://github.com/bozheng-hit/VoCapXLM.

pdf
LayoutReader: Pre-training of Text and Layout for Reading Order Detection
Zilong Wang | Yiheng Xu | Lei Cui | Jingbo Shang | Furu Wei
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dataset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectrum of document types. This first-ever large-scale dataset unleashes the power of deep neural networks for reading order detection. Specifically, our proposed LayoutReader captures the text and layout information for reading order prediction using the seq2seq model. It performs almost perfectly in reading order detection and significantly improves both open-source and commercial OCR engines in ordering text lines in their results in our experiments. The dataset and models are publicly available at https://aka.ms/layoutreader.

pdf
Jointly Learning to Repair Code and Generate Commit Message
Jiaqi Bai | Long Zhou | Ambrosio Blanco | Shujie Liu | Furu Wei | Ming Zhou | Zhoujun Li
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

We propose a novel task of jointly repairing program codes and generating commit messages. Code repair and commit message generation are two essential and related tasks for software development. However, existing work usually performs the two tasks independently. We construct a multilingual triple dataset including buggy code, fixed code, and commit messages for this novel task. We first introduce a cascaded method with two models, one is to generate the fixed code first, and the other generates the commit message based on the fixed and original codes. We enhance the cascaded method with different training approaches, including the teacher-student method, the multi-task method, and the back-translation method. To deal with the error propagation problem of the cascaded method, we also propose a joint model that can both repair the program code and generate the commit message in a unified framework. Massive experiments on our constructed buggy-fixed-commit dataset reflect the challenge of this task and that the enhanced cascaded model and the proposed joint model significantly outperform baselines in both quality of code and commit messages.

pdf
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression
Canwen Xu | Wangchunshu Zhou | Tao Ge | Ke Xu | Julian McAuley | Furu Wei
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recent studies on compression of pretrained language models (e.g., BERT) usually use preserved accuracy as the metric for evaluation. In this paper, we propose two new metrics, label loyalty and probability loyalty that measure how closely a compressed model (i.e., student) mimics the original model (i.e., teacher). We also explore the effect of compression with regard to robustness under adversarial attacks. We benchmark quantization, pruning, knowledge distillation and progressive module replacing with loyalty and robustness. By combining multiple compression techniques, we provide a practical strategy to achieve better accuracy, loyalty and robustness.

pdf
LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding
Yang Xu | Yiheng Xu | Tengchao Lv | Lei Cui | Furu Wei | Guoxin Wang | Yijuan Lu | Dinei Florencio | Cha Zhang | Wanxiang Che | Min Zhang | Lidong Zhou
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)

Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make it better capture the cross-modality interaction in the pre-training stage. Meanwhile, it also integrates a spatial-aware self-attention mechanism into the Transformer architecture so that the model can fully understand the relative positional relationship among different text blocks. Experiment results show that LayoutLMv2 outperforms LayoutLM by a large margin and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including FUNSD (0.7895 to 0.8420), CORD (0.9493 to 0.9601), SROIE (0.9524 to 0.9781), Kleister-NDA (0.8340 to 0.8520), RVL-CDIP (0.9443 to 0.9564), and DocVQA (0.7295 to 0.8672).

pdf
Consistency Regularization for Cross-Lingual Fine-Tuning
Bo Zheng | Li Dong | Shaohan Huang | Wenhui Wang | Zewen Chi | Saksham Singhal | Wanxiang Che | Ting Liu | Xia Song | Furu Wei
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)

Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we use example consistency regularization to penalize the prediction sensitivity to four types of data augmentations, i.e., subword sampling, Gaussian noise, code-switch substitution, and machine translation. In addition, we employ model consistency to regularize the models trained with two augmented versions of the same training set. Experimental results on the XTREME benchmark show that our method significantly improves cross-lingual fine-tuning across various tasks, including text classification, question answering, and sequence labeling.

pdf
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment
Zewen Chi | Li Dong | Bo Zheng | Shaohan Huang | Xian-Ling Mao | Heyan Huang | Furu Wei
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)

The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task. Specifically, the model first self-label word alignments for parallel sentences. Then we randomly mask tokens in a bitext pair. Given a masked token, the model uses a pointer network to predict the aligned token in the other language. We alternately perform the above two steps in an expectation-maximization manner. Experimental results show that our method improves cross-lingual transferability on various datasets, especially on the token-level tasks, such as question answering, and structured prediction. Moreover, the model can serve as a pretrained word aligner, which achieves reasonably low error rate on the alignment benchmarks. The code and pretrained parameters are available at github.com/CZWin32768/XLM-Align.

pdf
SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation
Shuo Ren | Long Zhou | Shujie Liu | Furu Wei | Ming Zhou | Shuai Ma
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)

While pre-training techniques are working very well in natural language processing, how to pre-train a decoder and effectively use it for neural machine translation (NMT) still remains a tricky issue. The main reason is that the cross-attention module between the encoder and decoder cannot be pre-trained, and the combined encoder-decoder model cannot work well in the fine-tuning stage because the inputs of the decoder cross-attention come from unknown encoder outputs. In this paper, we propose a better pre-training method for NMT by defining a semantic interface (SemFace) between the pre-trained encoder and the pre-trained decoder. Specifically, we propose two types of semantic interfaces, including CL-SemFace which regards cross-lingual embeddings as an interface, and VQ-SemFace which employs vector quantized embeddings to constrain the encoder outputs and decoder inputs in the same language-independent space. We conduct massive experiments on six supervised translation pairs and three unsupervised pairs. Experimental results demonstrate that our proposed SemFace can effectively connect the pre-trained encoder and decoder, and achieves significant improvement by 3.7 and 1.5 BLEU points on the two tasks respectively compared with previous pre-training-based NMT models.

pdf
Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
Xin Sun | Tao Ge | Furu Wei | Houfeng 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)

In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC). SAD optimizes the online inference efficiency for GEC by two innovations: 1) it aggressively decodes as many tokens as possible in parallel instead of always decoding only one token in each step to improve computational parallelism; 2) it uses a shallow decoder instead of the conventional Transformer architecture with balanced encoder-decoder depth to reduce the computational cost during inference. Experiments in both English and Chinese GEC benchmarks show that aggressive decoding could yield identical predictions to greedy decoding but with significant speedup for online inference. Its combination with the shallow decoder could offer an even higher online inference speedup over the powerful Transformer baseline without quality loss. Not only does our approach allow a single model to achieve the state-of-the-art results in English GEC benchmarks: 66.4 F0.5 in the CoNLL-14 and 72.9 F0.5 in the BEA-19 test set with an almost 10x online inference speedup over the Transformer-big model, but also it is easily adapted to other languages. Our code is available at https://github.com/AutoTemp/Shallow-Aggressive-Decoding.

pdf
xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering
Nan Yang | Furu Wei | Binxing Jiao | Daxing Jiang | Linjun Yang
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)

Dense passage retrieval has been shown to be an effective approach for information retrieval tasks such as open domain question answering. Under this paradigm, a dual-encoder model is learned to encode questions and passages separately into vector representations, and all the passage vectors are then pre-computed and indexed, which can be efficiently retrieved by vector space search during inference time. In this paper, we propose a new contrastive learning method called Cross Momentum Contrastive learning (xMoCo), for learning a dual-encoder model for question-passage matching. Our method efficiently maintains a large pool of negative samples like the original MoCo, and by jointly optimizing question-to-passage and passage-to-question matching tasks, enables using separate encoders for questions and passages. We evaluate our method on various open-domain question answering dataset, and the experimental results show the effectiveness of the proposed method.

pdf
Multilingual Agreement for Multilingual Neural Machine Translation
Jian Yang | Yuwei Yin | Shuming Ma | Haoyang Huang | Dongdong Zhang | Zhoujun Li | Furu Wei
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)

Although multilingual neural machine translation (MNMT) enables multiple language translations, the training process is based on independent multilingual objectives. Most multilingual models can not explicitly exploit different language pairs to assist each other, ignoring the relationships among them. In this work, we propose a novel agreement-based method to encourage multilingual agreement among different translation directions, which minimizes the differences among them. We combine the multilingual training objectives with the agreement term by randomly substituting some fragments of the source language with their counterpart translations of auxiliary languages. To examine the effectiveness of our method, we conduct experiments on the multilingual translation task of 10 language pairs. Experimental results show that our method achieves significant improvements over the previous multilingual baselines.

pdf
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
Canwen Xu | Wangchunshu Zhou | Tao Ge | Ke Xu | Julian McAuley | Furu Wei
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Cant is important for understanding advertising, comedies and dog-whistle politics. However, computational research on cant is hindered by a lack of available datasets. In this paper, we propose a large and diverse Chinese dataset for creating and understanding cant from a computational linguistics perspective. We formulate a task for cant understanding and provide both quantitative and qualitative analysis for tested word embedding similarity and pretrained language models. Experiments suggest that such a task requires deep language understanding, common sense, and world knowledge and thus can be a good testbed for pretrained language models and help models perform better on other tasks.

pdf
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
Zewen Chi | Li Dong | Furu Wei | Nan Yang | Saksham Singhal | Wenhui Wang | Xia Song | Xian-Ling Mao | Heyan Huang | Ming Zhou
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better understand the existing methods for learning cross-lingual representations. More importantly, inspired by the framework, we propose a new pre-training task based on contrastive learning. Specifically, we regard a bilingual sentence pair as two views of the same meaning and encourage their encoded representations to be more similar than the negative examples. By leveraging both monolingual and parallel corpora, we jointly train the pretext tasks to improve the cross-lingual transferability of pre-trained models. Experimental results on several benchmarks show that our approach achieves considerably better performance. The code and pre-trained models are available at https://aka.ms/infoxlm.

pdf
Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task
Jian Yang | Shuming Ma | Haoyang Huang | Dongdong Zhang | Li Dong | Shaohan Huang | Alexandre Muzio | Saksham Singhal | Hany Hassan | Xia Song | Furu Wei
Proceedings of the Sixth Conference on Machine Translation

This report describes Microsoft’s machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. We participated in all three evaluation tracks including Large Track and two Small Tracks where the former one is unconstrained and the latter two are fully constrained. Our model submissions to the shared task were initialized with DeltaLM, a generic pre-trained multilingual encoder-decoder model, and fine-tuned correspondingly with the vast collected parallel data and allowed data sources according to track settings, together with applying progressive learning and iterative back-translation approaches to further improve the performance. Our final submissions ranked first on three tracks in terms of the automatic evaluation metric.

2020

pdf bib
Can Monolingual Pretrained Models Help Cross-Lingual Classification?
Zewen Chi | Li Dong | Furu Wei | Xianling Mao | Heyan Huang
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

Multilingual pretrained language models (such as multilingual BERT) have achieved impressive results for cross-lingual transfer. However, due to the constant model capacity, multilingual pre-training usually lags behind the monolingual competitors. In this work, we present two approaches to improve zero-shot cross-lingual classification, by transferring the knowledge from monolingual pretrained models to multilingual ones. Experimental results on two cross-lingual classification benchmarks show that our methods outperform vanilla multilingual fine-tuning.

pdf
Investigating Learning Dynamics of BERT Fine-Tuning
Yaru Hao | Li Dong | Furu Wei | Ke Xu
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

The recently introduced pre-trained language model BERT advances the state-of-the-art on many NLP tasks through the fine-tuning approach, but few studies investigate how the fine-tuning process improves the model performance on downstream tasks. In this paper, we inspect the learning dynamics of BERT fine-tuning with two indicators. We use JS divergence to detect the change of the attention mode and use SVCCA distance to examine the change to the feature extraction mode during BERT fine-tuning. We conclude that BERT fine-tuning mainly changes the attention mode of the last layers and modifies the feature extraction mode of the intermediate and last layers. Moreover, we analyze the consistency of BERT fine-tuning between different random seeds and different datasets. In summary, we provide a distinctive understanding of the learning dynamics of BERT fine-tuning, which sheds some light on improving the fine-tuning results.

pdf
UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database
Canwen Xu | Tao Ge | Chenliang Li | Furu Wei
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

Chinese and Japanese share many characters with similar surface morphology. To better utilize the shared knowledge across the languages, we propose UnihanLM, a self-supervised Chinese-Japanese pretrained masked language model (MLM) with a novel two-stage coarse-to-fine training approach. We exploit Unihan, a ready-made database constructed by linguistic experts to first merge morphologically similar characters into clusters. The resulting clusters are used to replace the original characters in sentences for the coarse-grained pretraining of the MLM. Then, we restore the clusters back to the original characters in sentences for the fine-grained pretraining to learn the representation of the specific characters. We conduct extensive experiments on a variety of Chinese and Japanese NLP benchmarks, showing that our proposed UnihanLM is effective on both mono- and cross-lingual Chinese and Japanese tasks, shedding light on a new path to exploit the homology of languages.

pdf
Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths
Haozhe Ji | Pei Ke | Shaohan Huang | Furu Wei | Minlie Huang
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

Commonsense explanation generation aims to empower the machine’s sense-making capability by generating plausible explanations to statements against commonsense. While this task is easy to human, the machine still struggles to generate reasonable and informative explanations. In this work, we propose a method that first extracts the underlying concepts which are served as bridges in the reasoning chain and then integrates these concepts to generate the final explanation. To facilitate the reasoning process, we utilize external commonsense knowledge to build the connection between a statement and the bridge concepts by extracting and pruning multi-hop paths to build a subgraph. We design a bridge concept extraction model that first scores the triples, routes the paths in the subgraph, and further selects bridge concepts with weak supervision at both the triple level and the concept level. We conduct experiments on the commonsense explanation generation task and our model outperforms the state-of-the-art baselines in both automatic and human evaluation.

pdf
DocBank: A Benchmark Dataset for Document Layout Analysis
Minghao Li | Yiheng Xu | Lei Cui | Shaohan Huang | Furu Wei | Zhoujun Li | Ming Zhou
Proceedings of the 28th International Conference on Computational Linguistics

Document layout analysis usually relies on computer vision models to understand documents while ignoring textual information that is vital to capture. Meanwhile, high quality labeled datasets with both visual and textual information are still insufficient. In this paper, we present DocBank, a benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the LaTeX documents available on the arXiv.com. With DocBank, models from different modalities can be compared fairly and multi-modal approaches will be further investigated and boost the performance of document layout analysis. We build several strong baselines and manually split train/dev/test sets for evaluation. Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents. The DocBank dataset is publicly available at https://github.com/doc-analysis/DocBank.

pdf
Unsupervised Fine-tuning for Text Clustering
Shaohan Huang | Furu Wei | Lei Cui | Xingxing Zhang | Ming Zhou
Proceedings of the 28th International Conference on Computational Linguistics

Fine-tuning with pre-trained language models (e.g. BERT) has achieved great success in many language understanding tasks in supervised settings (e.g. text classification). However, relatively little work has been focused on applying pre-trained models in unsupervised settings, such as text clustering. In this paper, we propose a novel method to fine-tune pre-trained models unsupervisedly for text clustering, which simultaneously learns text representations and cluster assignments using a clustering oriented loss. Experiments on three text clustering datasets (namely TREC-6, Yelp, and DBpedia) show that our model outperforms the baseline methods and achieves state-of-the-art results.

pdf
At Which Level Should We Extract? An Empirical Analysis on Extractive Document Summarization
Qingyu Zhou | Furu Wei | Ming Zhou
Proceedings of the 28th International Conference on Computational Linguistics

Extractive methods have been proven effective in automatic document summarization. Previous works perform this task by identifying informative contents at sentence level. However, it is unclear whether performing extraction at sentence level is the best solution. In this work, we show that unnecessity and redundancy issues exist when extracting full sentences, and extracting sub-sentential units is a promising alternative. Specifically, we propose extracting sub-sentential units based on the constituency parsing tree. A neural extractive model which leverages the sub-sentential information and extracts them is presented. Extensive experiments and analyses show that extracting sub-sentential units performs competitively comparing to full sentence extraction under the evaluation of both automatic and human evaluations. Hopefully, our work could provide some inspiration of the basic extraction units in extractive summarization for future research.

pdf
Harvesting and Refining Question-Answer Pairs for Unsupervised QA
Zhongli Li | Wenhui Wang | Li Dong | Furu Wei | Ke Xu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Question Answering (QA) has shown great success thanks to the availability of large-scale datasets and the effectiveness of neural models. Recent research works have attempted to extend these successes to the settings with few or no labeled data available. In this work, we introduce two approaches to improve unsupervised QA. First, we harvest lexically and syntactically divergent questions from Wikipedia to automatically construct a corpus of question-answer pairs (named as RefQA). Second, we take advantage of the QA model to extract more appropriate answers, which iteratively refines data over RefQA. We conduct experiments on SQuAD 1.1, and NewsQA by fine-tuning BERT without access to manually annotated data. Our approach outperforms previous unsupervised approaches by a large margin, and is competitive with early supervised models. We also show the effectiveness of our approach in the few-shot learning setting.

pdf
Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph
Haozhe Ji | Pei Ke | Shaohan Huang | Furu Wei | Xiaoyan Zhu | Minlie Huang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge is required during generation. Existing approaches that integrate commonsense knowledge into generative pre-trained language models simply transfer relational knowledge by post-training on individual knowledge triples while ignoring rich connections within the knowledge graph. We argue that exploiting both the structural and semantic information of the knowledge graph facilitates commonsense-aware text generation. In this paper, we propose Generation with Multi-Hop Reasoning Flow (GRF) that enables pre-trained models with dynamic multi-hop reasoning on multi-relational paths extracted from the external commonsense knowledge graph. We empirically show that our model outperforms existing baselines on three text generation tasks that require reasoning over commonsense knowledge. We also demonstrate the effectiveness of the dynamic multi-hop reasoning module with reasoning paths inferred by the model that provide rationale to the generation.

pdf
Pre-training for Abstractive Document Summarization by Reinstating Source Text
Yanyan Zou | Xingxing Zhang | Wei Lu | Furu Wei | Ming Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Abstractive document summarization is usually modeled as a sequence-to-sequence (SEQ2SEQ) learning problem. Unfortunately, training large SEQ2SEQ based summarization models on limited supervised summarization data is challenging. This paper presents three sequence-to-sequence pre-training (in shorthand, STEP) objectives which allow us to pre-train a SEQ2SEQ based abstractive summarization model on unlabeled text. The main idea is that, given an input text artificially constructed from a document, a model is pre-trained to reinstate the original document. These objectives include sentence reordering, next sentence generation and masked document generation, which have close relations with the abstractive document summarization task. Experiments on two benchmark summarization datasets (i.e., CNN/DailyMail and New York Times) show that all three objectives can improve performance upon baselines. Compared to models pre-trained on large-scale data (larger than 160GB), our method, with only 19GB text for pre-training, achieves comparable results, which demonstrates its effectiveness.

pdf
Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction
Mengyun Chen | Tao Ge | Xingxing Zhang | Furu Wei | Ming Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We propose a novel language-independent approach to improve the efficiency for Grammatical Error Correction (GEC) by dividing the task into two subtasks: Erroneous Span Detection (ESD) and Erroneous Span Correction (ESC). ESD identifies grammatically incorrect text spans with an efficient sequence tagging model. Then, ESC leverages a seq2seq model to take the sentence with annotated erroneous spans as input and only outputs the corrected text for these spans. Experiments show our approach performs comparably to conventional seq2seq approaches in both English and Chinese GEC benchmarks with less than 50% time cost for inference.

pdf
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing
Canwen Xu | Wangchunshu Zhou | Tao Ge | Furu Wei | Ming Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, we propose a novel model compression approach to effectively compress BERT by progressive module replacing. Our approach first divides the original BERT into several modules and builds their compact substitutes. Then, we randomly replace the original modules with their substitutes to train the compact modules to mimic the behavior of the original modules. We progressively increase the probability of replacement through the training. In this way, our approach brings a deeper level of interaction between the original and compact models. Compared to the previous knowledge distillation approaches for BERT compression, our approach does not introduce any additional loss function. Our approach outperforms existing knowledge distillation approaches on GLUE benchmark, showing a new perspective of model compression.

pdf
TableBank: Table Benchmark for Image-based Table Detection and Recognition
Minghao Li | Lei Cui | Shaohan Huang | Furu Wei | Ming Zhou | Zhoujun Li
Proceedings of the Twelfth Language Resources and Evaluation Conference

We present TableBank, a new image-based table detection and recognition dataset built with novel weak supervision from Word and Latex documents on the internet. Existing research for image-based table detection and recognition usually fine-tunes pre-trained models on out-of-domain data with a few thousand human-labeled examples, which is difficult to generalize on real-world applications. With TableBank that contains 417K high quality labeled tables, we build several strong baselines using state-of-the-art models with deep neural networks. We make TableBank publicly available and hope it will empower more deep learning approaches in the table detection and recognition task. The dataset and models can be downloaded from https://github.com/doc-analysis/TableBank.

pdf
Improving Grammatical Error Correction with Machine Translation Pairs
Wangchunshu Zhou | Tao Ge | Chang Mu | Ke Xu | Furu Wei | Ming Zhou
Findings of the Association for Computational Linguistics: EMNLP 2020

We propose a novel data synthesis method to generate diverse error-corrected sentence pairs for improving grammatical error correction, which is based on a pair of machine translation models (e.g., Chinese to English) of different qualities (i.e., poor and good). The poor translation model can resemble the ESL (English as a second language) learner and tends to generate translations of low quality in terms of fluency and grammaticality, while the good translation model generally generates fluent and grammatically correct translations. With the pair of translation models, we can generate unlimited numbers of poor to good English sentence pairs from text in the source language (e.g., Chinese) of the translators. Our approach can generate various error-corrected patterns and nicely complement the other data synthesis approaches for GEC. Experimental results demonstrate the data generated by our approach can effectively help a GEC model to improve the performance and achieve the state-of-the-art single-model performance in BEA-19 and CoNLL-14 benchmark datasets.

pdf
Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers
Shusheng Xu | Xingxing Zhang | Yi Wu | Furu Wei | Ming Zhou
Findings of the Association for Computational Linguistics: EMNLP 2020

Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge weights measured by sentence similarities. In this work, we find that transformer attentions can be used to rank sentences for unsupervised extractive summarization. Specifically, we first pre-train a hierarchical transformer model using unlabeled documents only. Then we propose a method to rank sentences using sentence-level self-attentions and pre-training objectives. Experiments on CNN/DailyMail and New York Times datasets show our model achieves state-of-the-art performance on unsupervised summarization. We also find in experiments that our model is less dependent on sentence positions. When using a linear combination of our model and a recent unsupervised model explicitly modeling sentence positions, we obtain even better results.

pdf
Scheduled DropHead: A Regularization Method for Transformer Models
Wangchunshu Zhou | Tao Ge | Furu Wei | Ming Zhou | Ke Xu
Findings of the Association for Computational Linguistics: EMNLP 2020

We introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism which is a key component of transformer. In contrast to the conventional dropout mechanism which randomly drops units or connections, DropHead drops entire attention heads during training to prevent the multi-head attention model from being dominated by a small portion of attention heads. It can help reduce the risk of overfitting and allow the models to better benefit from the multi-head attention. Given the interaction between multi-headedness and training dynamics, we further propose a novel dropout rate scheduler to adjust the dropout rate of DropHead throughout training, which results in a better regularization effect. Experimental results demonstrate that our proposed approach can improve transformer models by 0.9 BLEU score on WMT14 En-De translation task and around 1.0 accuracy for various text classification tasks.

2019

pdf
Video Dialog via Progressive Inference and Cross-Transformer
Weike Jin | Zhou Zhao | Mao Gu | Jun Xiao | Furu Wei | Yueting Zhuang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Video dialog is a new and challenging task, which requires the agent to answer questions combining video information with dialog history. And different from single-turn video question answering, the additional dialog history is important for video dialog, which often includes contextual information for the question. Existing visual dialog methods mainly use RNN to encode the dialog history as a single vector representation, which might be rough and straightforward. Some more advanced methods utilize hierarchical structure, attention and memory mechanisms, which still lack an explicit reasoning process. In this paper, we introduce a novel progressive inference mechanism for video dialog, which progressively updates query information based on dialog history and video content until the agent think the information is sufficient and unambiguous. In order to tackle the multi-modal fusion problem, we propose a cross-transformer module, which could learn more fine-grained and comprehensive interactions both inside and between the modalities. And besides answer generation, we also consider question generation, which is more challenging but significant for a complete video dialog system. We evaluate our method on two large-scale datasets, and the extensive experiments show the effectiveness of our method.

pdf
Visualizing and Understanding the Effectiveness of BERT
Yaru Hao | Li Dong | Furu Wei | Ke Xu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different tasks. In this paper, we propose to visualize loss landscapes and optimization trajectories of fine-tuning BERT on specific datasets. First, we find that pre-training reaches a good initial point across downstream tasks, which leads to wider optima and easier optimization compared with training from scratch. We also demonstrate that the fine-tuning procedure is robust to overfitting, even though BERT is highly over-parameterized for downstream tasks. Second, the visualization results indicate that fine-tuning BERT tends to generalize better because of the flat and wide optima, and the consistency between the training loss surface and the generalization error surface. Third, the lower layers of BERT are more invariant during fine-tuning, which suggests that the layers that are close to input learn more transferable representations of language.

pdf bib
Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension
Hangbo Bao | Li Dong | Furu Wei | Wenhui Wang | Nan Yang | Lei Cui | Songhao Piao | Ming Zhou
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

Most machine reading comprehension (MRC) models separately handle encoding and matching with different network architectures. In contrast, pretrained language models with Transformer layers, such as GPT (Radford et al., 2018) and BERT (Devlin et al., 2018), have achieved competitive performance on MRC. A research question that naturally arises is: apart from the benefits of pre-training, how many performance gain comes from the unified network architecture. In this work, we evaluate and analyze unifying encoding and matching components with Transformer for the MRC task. Experimental results on SQuAD show that the unified model outperforms previous networks that separately treat encoding and matching. We also introduce a metric to inspect whether a Transformer layer tends to perform encoding or matching. The analysis results show that the unified model learns different modeling strategies compared with previous manually-designed models.

pdf
BERT-based Lexical Substitution
Wangchunshu Zhou | Tao Ge | Ke Xu | Furu Wei | Ming Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Previous studies on lexical substitution tend to obtain substitute candidates by finding the target word’s synonyms from lexical resources (e.g., WordNet) and then rank the candidates based on its contexts. These approaches have two limitations: (1) They are likely to overlook good substitute candidates that are not the synonyms of the target words in the lexical resources; (2) They fail to take into account the substitution’s influence on the global context of the sentence. To address these issues, we propose an end-to-end BERT-based lexical substitution approach which can propose and validate substitute candidates without using any annotated data or manually curated resources. Our approach first applies dropout to the target word’s embedding for partially masking the word, allowing BERT to take balanced consideration of the target word’s semantics and contexts for proposing substitute candidates, and then validates the candidates based on their substitution’s influence on the global contextualized representation of the sentence. Experiments show our approach performs well in both proposing and ranking substitute candidates, achieving the state-of-the-art results in both LS07 and LS14 benchmarks.

pdf
Retrieval-Enhanced Adversarial Training for Neural Response Generation
Qingfu Zhu | Lei Cui | Wei-Nan Zhang | Furu Wei | Ting Liu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing approaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows that the REAT method significantly outperforms the vanilla Seq2Seq model as well as the conventional adversarial training approach.

pdf
Learning to Ask Unanswerable Questions for Machine Reading Comprehension
Haichao Zhu | Li Dong | Furu Wei | Wenhui Wang | Bing Qin | Ting Liu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Machine reading comprehension with unanswerable questions is a challenging task. In this work, we propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer. We introduce a pair-to-sequence model for unanswerable question generation, which effectively captures the interactions between the question and the paragraph. We also present a way to construct training data for our question generation models by leveraging the existing reading comprehension dataset. Experimental results show that the pair-to-sequence model performs consistently better compared with the sequence-to-sequence baseline. We further use the automatically generated unanswerable questions as a means of data augmentation on the SQuAD 2.0 dataset, yielding 1.9 absolute F1 improvement with BERT-base model and 1.7 absolute F1 improvement with BERT-large model.

pdf
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
Xingxing Zhang | Furu Wei | Ming Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder with these inaccurate labels is challenging. Inspired by the recent work on pre-training transformer sentence encoders (Devlin et al., 2018), we propose Hibert (as shorthand for HIerachical Bidirectional Encoder Representations from Transformers) for document encoding and a method to pre-train it using unlabeled data. We apply the pre-trained Hibert to our summarization model and it outperforms its randomly initialized counterpart by 1.25 ROUGE on the CNN/Dailymail dataset and by 2.0 ROUGE on a version of New York Times dataset. We also achieve the state-of-the-art performance on these two datasets.

pdf
Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study
Tao Ge | Xingxing Zhang | Furu Wei | Ming Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Sequence-to-sequence (seq2seq) models have achieved tremendous success in text generation tasks. However, there is no guarantee that they can always generate sentences without grammatical errors. In this paper, we present a preliminary empirical study on whether and how much automatic grammatical error correction can help improve seq2seq text generation. We conduct experiments across various seq2seq text generation tasks including machine translation, formality style transfer, sentence compression and simplification. Experiments show the state-of-the-art grammatical error correction system can improve the grammaticality of generated text and can bring task-oriented improvements in the tasks where target sentences are in a formal style.

2018

pdf
Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization
Ziqiang Cao | Wenjie Li | Sujian Li | Furu Wei
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most previous seq2seq summarization systems purely depend on the source text to generate summaries, which tends to work unstably. Inspired by the traditional template-based summarization approaches, this paper proposes to use existing summaries as soft templates to guide the seq2seq model. To this end, we use a popular IR platform to Retrieve proper summaries as candidate templates. Then, we extend the seq2seq framework to jointly conduct template Reranking and template-aware summary generation (Rewriting). Experiments show that, in terms of informativeness, our model significantly outperforms the state-of-the-art methods, and even soft templates themselves demonstrate high competitiveness. In addition, the import of high-quality external summaries improves the stability and readability of generated summaries.

pdf
Neural Document Summarization by Jointly Learning to Score and Select Sentences
Qingyu Zhou | Nan Yang | Furu Wei | Shaohan Huang | Ming Zhou | Tiejun Zhao
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Sentence scoring and sentence selection are two main steps in extractive document summarization systems. However, previous works treat them as two separated subtasks. In this paper, we present a novel end-to-end neural network framework for extractive document summarization by jointly learning to score and select sentences. It first reads the document sentences with a hierarchical encoder to obtain the representation of sentences. Then it builds the output summary by extracting sentences one by one. Different from previous methods, our approach integrates the selection strategy into the scoring model, which directly predicts the relative importance given previously selected sentences. Experiments on the CNN/Daily Mail dataset show that the proposed framework significantly outperforms the state-of-the-art extractive summarization models.

pdf
Fluency Boost Learning and Inference for Neural Grammatical Error Correction
Tao Ge | Furu Wei | Ming Zhou
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most of the neural sequence-to-sequence (seq2seq) models for grammatical error correction (GEC) have two limitations: (1) a seq2seq model may not be well generalized with only limited error-corrected data; (2) a seq2seq model may fail to completely correct a sentence with multiple errors through normal seq2seq inference. We attempt to address these limitations by proposing a fluency boost learning and inference mechanism. Fluency boosting learning generates fluency-boost sentence pairs during training, enabling the error correction model to learn how to improve a sentence’s fluency from more instances, while fluency boosting inference allows the model to correct a sentence incrementally with multiple inference steps until the sentence’s fluency stops increasing. Experiments show our approaches improve the performance of seq2seq models for GEC, achieving state-of-the-art results on both CoNLL-2014 and JFLEG benchmark datasets.

pdf
Neural Open Information Extraction
Lei Cui | Furu Wei | Ming Zhou
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Conventional Open Information Extraction (Open IE) systems are usually built on hand-crafted patterns from other NLP tools such as syntactic parsing, yet they face problems of error propagation. In this paper, we propose a neural Open IE approach with an encoder-decoder framework. Distinct from existing methods, the neural Open IE approach learns highly confident arguments and relation tuples bootstrapped from a state-of-the-art Open IE system. An empirical study on a large benchmark dataset shows that the neural Open IE system significantly outperforms several baselines, while maintaining comparable computational efficiency.

pdf
EventWiki: A Knowledge Base of Major Events
Tao Ge | Lei Cui | Baobao Chang | Zhifang Sui | Furu Wei | Ming Zhou
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf
Neural Latent Extractive Document Summarization
Xingxing Zhang | Mirella Lapata | Furu Wei | Ming Zhou
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Extractive summarization models need sentence level labels, which are usually created with rule-based methods since most summarization datasets only have document summary pairs. These labels might be suboptimal. We propose a latent variable extractive model, where sentences are viewed as latent variables and sentences with activated variables are used to infer gold summaries. During training, the loss can come directly from gold summaries. Experiments on CNN/Dailymail dataset show our latent extractive model outperforms a strong extractive baseline trained on rule-based labels and also performs competitively with several recent models.

pdf
Attention-Guided Answer Distillation for Machine Reading Comprehension
Minghao Hu | Yuxing Peng | Furu Wei | Zhen Huang | Dongsheng Li | Nan Yang | Ming Zhou
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also vulnerable to adversarial attacks. This paper tackles these problems by leveraging knowledge distillation, which aims to transfer knowledge from an ensemble model to a single model. We first demonstrate that vanilla knowledge distillation applied to answer span prediction is effective for reading comprehension systems. We then propose two novel approaches that not only penalize the prediction on confusing answers but also guide the training with alignment information distilled from the ensemble. Experiments show that our best student model has only a slight drop of 0.4% F1 on the SQuAD test set compared to the ensemble teacher, while running 12x faster during inference. It even outperforms the teacher on adversarial SQuAD datasets and NarrativeQA benchmark.

pdf
Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition
Tao Ge | Qing Dou | Heng Ji | Lei Cui | Baobao Chang | Zhifang Sui | Furu Wei | Ming Zhou
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

This paper proposes to study fine-grained coordinated cross-lingual text stream alignment through a novel information network decipherment paradigm. We use Burst Information Networks as media to represent text streams and present a simple yet effective network decipherment algorithm with diverse clues to decipher the networks for accurate text stream alignment. Experiments on Chinese-English news streams show our approach not only outperforms previous approaches on bilingual lexicon extraction from coordinated text streams but also can harvest high-quality alignments from large amounts of streaming data for endless language knowledge mining, which makes it promising to be a new paradigm for automatic language knowledge acquisition.

2017

pdf
Gated Self-Matching Networks for Reading Comprehension and Question Answering
Wenhui Wang | Nan Yang | Furu Wei | Baobao Chang | Ming Zhou
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we present the gated self-matching networks for reading comprehension style question answering, which aims to answer questions from a given passage. We first match the question and passage with gated attention-based recurrent networks to obtain the question-aware passage representation. Then we propose a self-matching attention mechanism to refine the representation by matching the passage against itself, which effectively encodes information from the whole passage. We finally employ the pointer networks to locate the positions of answers from the passages. We conduct extensive experiments on the SQuAD dataset. The single model achieves 71.3% on the evaluation metrics of exact match on the hidden test set, while the ensemble model further boosts the results to 75.9%. At the time of submission of the paper, our model holds the first place on the SQuAD leaderboard for both single and ensemble model.

pdf
Selective Encoding for Abstractive Sentence Summarization
Qingyu Zhou | Nan Yang | Furu Wei | Ming Zhou
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose a selective encoding model to extend the sequence-to-sequence framework for abstractive sentence summarization. It consists of a sentence encoder, a selective gate network, and an attention equipped decoder. The sentence encoder and decoder are built with recurrent neural networks. The selective gate network constructs a second level sentence representation by controlling the information flow from encoder to decoder. The second level representation is tailored for sentence summarization task, which leads to better performance. We evaluate our model on the English Gigaword, DUC 2004 and MSR abstractive sentence summarization datasets. The experimental results show that the proposed selective encoding model outperforms the state-of-the-art baseline models.

pdf
SuperAgent: A Customer Service Chatbot for E-commerce Websites
Lei Cui | Shaohan Huang | Furu Wei | Chuanqi Tan | Chaoqun Duan | Ming Zhou
Proceedings of ACL 2017, System Demonstrations

pdf
Learning to Generate Product Reviews from Attributes
Li Dong | Shaohan Huang | Furu Wei | Mirella Lapata | Ming Zhou | Ke Xu
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

Automatically generating product reviews is a meaningful, yet not well-studied task in sentiment analysis. Traditional natural language generation methods rely extensively on hand-crafted rules and predefined templates. This paper presents an attention-enhanced attribute-to-sequence model to generate product reviews for given attribute information, such as user, product, and rating. The attribute encoder learns to represent input attributes as vectors. Then, the sequence decoder generates reviews by conditioning its output on these vectors. We also introduce an attention mechanism to jointly generate reviews and align words with input attributes. The proposed model is trained end-to-end to maximize the likelihood of target product reviews given the attributes. We build a publicly available dataset for the review generation task by leveraging the Amazon book reviews and their metadata. Experiments on the dataset show that our approach outperforms baseline methods and the attention mechanism significantly improves the performance of our model.

pdf
Entity Linking for Queries by Searching Wikipedia Sentences
Chuanqi Tan | Furu Wei | Pengjie Ren | Weifeng Lv | Ming Zhou
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We present a simple yet effective approach for linking entities in queries. The key idea is to search sentences similar to a query from Wikipedia articles and directly use the human-annotated entities in the similar sentences as candidate entities for the query. Then, we employ a rich set of features, such as link-probability, context-matching, word embeddings, and relatedness among candidate entities as well as their related entities, to rank the candidates under a regression based framework. The advantages of our approach lie in two aspects, which contribute to the ranking process and final linking result. First, it can greatly reduce the number of candidate entities by filtering out irrelevant entities with the words in the query. Second, we can obtain the query sensitive prior probability in addition to the static link-probability derived from all Wikipedia articles. We conduct experiments on two benchmark datasets on entity linking for queries, namely the ERD14 dataset and the GERDAQ dataset. Experimental results show that our method outperforms state-of-the-art systems and yields 75.0% in F1 on the ERD14 dataset and 56.9% on the GERDAQ dataset.

2016

pdf
Solving and Generating Chinese Character Riddles
Chuanqi Tan | Furu Wei | Li Dong | Weifeng Lv | Ming Zhou
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf
A Redundancy-Aware Sentence Regression Framework for Extractive Summarization
Pengjie Ren | Furu Wei | Zhumin Chen | Jun Ma | Ming Zhou
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Existing sentence regression methods for extractive summarization usually model sentence importance and redundancy in two separate processes. They first evaluate the importance f(s) of each sentence s and then select sentences to generate a summary based on both the importance scores and redundancy among sentences. In this paper, we propose to model importance and redundancy simultaneously by directly evaluating the relative importance f(s|S) of a sentence s given a set of selected sentences S. Specifically, we present a new framework to conduct regression with respect to the relative gain of s given S calculated by the ROUGE metric. Besides the single sentence features, additional features derived from the sentence relations are incorporated. Experiments on the DUC 2001, 2002 and 2004 multi-document summarization datasets show that the proposed method outperforms state-of-the-art extractive summarization approaches.

pdf
AttSum: Joint Learning of Focusing and Summarization with Neural Attention
Ziqiang Cao | Wenjie Li | Sujian Li | Furu Wei | Yanran Li
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Query relevance ranking and sentence saliency ranking are the two main tasks in extractive query-focused summarization. Previous supervised summarization systems often perform the two tasks in isolation. However, since reference summaries are the trade-off between relevance and saliency, using them as supervision, neither of the two rankers could be trained well. This paper proposes a novel summarization system called AttSum, which tackles the two tasks jointly. It automatically learns distributed representations for sentences as well as the document cluster. Meanwhile, it applies the attention mechanism to simulate the attentive reading of human behavior when a query is given. Extensive experiments are conducted on DUC query-focused summarization benchmark datasets. Without using any hand-crafted features, AttSum achieves competitive performance. We also observe that the sentences recognized to focus on the query indeed meet the query need.

2015

pdf
Splusplus: A Feature-Rich Two-stage Classifier for Sentiment Analysis of Tweets
Li Dong | Furu Wei | Yichun Yin | Ming Zhou | Ke Xu
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

pdf
Question Answering over Freebase with Multi-Column Convolutional Neural Networks
Li Dong | Furu Wei | Ming Zhou | Ke Xu
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)

pdf
A Dependency-Based Neural Network for Relation Classification
Yang Liu | Furu Wei | Sujian Li | Heng Ji | Ming Zhou | Houfeng Wang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

pdf
Learning Summary Prior Representation for Extractive Summarization
Ziqiang Cao | Furu Wei | Sujian Li | Wenjie Li | Ming Zhou | Houfeng Wang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

pdf bib
Cross-lingual Sentiment Lexicon Learning With Bilingual Word Graph Label Propagation
Dehong Gao | Furu Wei | Wenjie Li | Xiaohua Liu | Ming Zhou
Computational Linguistics, Volume 41, Issue 1 - March 2015

pdf
A Statistical Parsing Framework for Sentiment Classification
Li Dong | Furu Wei | Shujie Liu | Ming Zhou | Ke Xu
Computational Linguistics, Volume 41, Issue 2 - June 2015

2014

pdf
A Joint Segmentation and Classification Framework for Sentiment Analysis
Duyu Tang | Furu Wei | Bing Qin | Li Dong | Ting Liu | Ming Zhou
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
Duyu Tang | Furu Wei | Nan Yang | Ming Zhou | Ting Liu | Bing Qin
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification
Li Dong | Furu Wei | Chuanqi Tan | Duyu Tang | Ming Zhou | Ke Xu
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf
Coooolll: A Deep Learning System for Twitter Sentiment Classification
Duyu Tang | Furu Wei | Bing Qin | Ting Liu | Ming Zhou
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)

pdf
Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach
Duyu Tang | Furu Wei | Bing Qin | Ming Zhou | Ting Liu
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf
Entity Linking for Tweets
Xiaohua Liu | Yitong Li | Haocheng Wu | Ming Zhou | Furu Wei | Yi Lu
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2012

pdf
Joint Inference of Named Entity Recognition and Normalization for Tweets
Xiaohua Liu | Ming Zhou | Xiangyang Zhou | Zhongyang Fu | Furu Wei
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
Cross-Lingual Mixture Model for Sentiment Classification
Xinfan Meng | Furu Wei | Xiaohua Liu | Ming Zhou | Ge Xu | Houfeng Wang
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf
QuickView: NLP-based Tweet Search
Xiaohua Liu | Furu Wei | Ming Zhou | QuickView Team Microsoft
Proceedings of the ACL 2012 System Demonstrations

pdf
Twitter Topic Summarization by Ranking Tweets using Social Influence and Content Quality
Yajuan Duan | Zhumin Chen | Furu Wei | Ming Zhou | Heung-Yeung Shum
Proceedings of COLING 2012

pdf
Graph-Based Multi-Tweet Summarization using Social Signals
Xiaohua Liu | Yitong Li | Furu Wei | Ming Zhou
Proceedings of COLING 2012

pdf
Lost in Translations? Building Sentiment Lexicons using Context Based Machine Translation
Xinfan Meng | Furu Wei | Ge Xu | Longkai Zhang | Xiaohua Liu | Ming Zhou | Houfeng Wang
Proceedings of COLING 2012: Posters

2011

pdf
Recognizing Named Entities in Tweets
Xiaohua Liu | Shaodian Zhang | Furu Wei | Ming Zhou
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2009

pdf
Co-Feedback Ranking for Query-Focused Summarization
Furu Wei | Wenjie Li | Yanxiang He
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers

2008

pdf
PNR2: Ranking Sentences with Positive and Negative Reinforcement for Query-Oriented Update Summarization
Wenjie Li | Furu Wei | Qin Lu | Yanxiang He
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf
Exploiting the Role of Position Feature in Chinese Relation Extraction
Peng Zhang | Wenjie Li | Furu Wei | Qin Lu | Yuexian Hou
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

Relation extraction is the task of finding pre-defined semantic relations between two entities or entity mentions from text. Many methods, such as feature-based and kernel-based methods, have been proposed in the literature. Among them, feature-based methods draw much attention from researchers. However, to the best of our knowledge, existing feature-based methods did not explicitly incorporate the position feature and no in-depth analysis was conducted in this regard. In this paper, we define and exploit nine types of position information between two named entity mentions and then use it along with other features in a multi-class classification framework for Chinese relation extraction. Experiments on the ACE 2005 data set show that the position feature is more effective than the other recognized features like entity type/subtype and character-based N-gram context. Most important, it can be easily captured and does not require as much effort as applying deep natural language processing.

pdf
A Novel Feature-based Approach to Chinese Entity Relation Extraction
Wenjie Li | Peng Zhang | Furu Wei | Yuexian Hou | Qin Lu
Proceedings of ACL-08: HLT, Short Papers

Search
Co-authors