Yinhe Zheng


2023

pdf
Long-Tailed Question Answering in an Open World
Yi Dai | Hao Lang | Yinhe Zheng | Fei Huang | Yongbin Li
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Real-world data often have an open long-tailed distribution, and building a unified QA model supporting various tasks is vital for practical QA applications.However, it is non-trivial to extend previous QA approaches since they either require access to seen tasks of adequate samples or do not explicitly model samples from unseen tasks.In this paper, we define Open Long-Tailed QA (OLTQA) as learning from long-tailed distributed data and optimizing performance over seen and unseen QA tasks.We propose an OLTQA model that encourages knowledge sharing between head, tail and unseen tasks, and explicitly mines knowledge from a large pre-trained language model (LM).Specifically, we organize our model through a pool of fine-grained components and dynamically combine these components for an input to facilitate knowledge sharing.A retrieve-then-rerank frame is further introduced to select in-context examples, which guild the LM to generate text that express knowledge for QA tasks.Moreover, a two-stage training approach is introduced to pre-train the framework by knowledge distillation (KD) from the LM and then jointly train the frame and a QA model through an adaptive mutual KD method.On a large-scale OLTQA dataset we curate from 43 existing QA datasets, our model consistently outperforms the state-of-the-art.

pdf
Domain Incremental Lifelong Learning in an Open World
Yi Dai | Hao Lang | Yinhe Zheng | Bowen Yu | Fei Huang | Yongbin Li
Findings of the Association for Computational Linguistics: ACL 2023

Lifelong learning (LL) is an important ability for NLP models to learn new tasks continuously. Architecture-based approaches are reported to be effective implementations for LL models. However, it is non-trivial to extend previous approaches to domain incremental LL scenarios since they either require access to task identities in the testing phase or cannot handle samples from unseen tasks. In this paper, we propose Diana: a dynamic architecture-based lifelong learning model that tries to learn a sequence of tasks with a prompt-enhanced language model. Four types of hierarchically organized prompts are used in Diana to capture knowledge from different granularities. Specifically, we dedicate task-level prompts to capture task-specific knowledge to retain high LL performances and maintain instance-level prompts to learn knowledge shared across input samples to improve the model’s generalization performance. Moreover, we dedicate separate prompts to explicitly model unseen tasks and introduce a set of prompt key vectors to facilitate knowledge sharing between tasks. Extensive experiments demonstrate that Diana outperforms state-of-the-art LL models, especially in handling unseen tasks.

2022

pdf
LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency
Haoxiang Shi | Rongsheng Zhang | Jiaan Wang | Cen Wang | Yinhe Zheng | Tetsuya Sakai
Proceedings of the 29th International Conference on Computational Linguistics

Pre-trained Language Models (PLMs) are the cornerstone of the modern Natural Language Processing (NLP). However, as PLMs become heavier, fine tuning all their parameters loses their efficiency. Existing parameter-efficient methods generally focus on reducing the trainable parameters in PLMs but neglect the inference speed, which limits the ability to deploy PLMs. In this paper, we propose LayerConnect (hypernetwork-assisted inter-layer connectors) to enhance inference efficiency. Specifically, a light-weight connector with a linear structure is inserted between two Transformer layers, and the parameters inside each connector are tuned by a hypernetwork comprising an interpolator and a down-sampler. We perform extensive experiments on the widely used the GLUE benchmark. The experimental results verify the inference efficiency of our model. Compared to Adapter, our model parameters are reduced to approximately 11.75%, while the performance degradation is kept to less than 5% (2.5 points on average).

pdf
Semi-Supervised Lifelong Language Learning
Yingxiu Zhao | Yinhe Zheng | Bowen Yu | Zhiliang Tian | Dongkyu Lee | Jian Sun | Yongbin Li | Nevin L. Zhang
Findings of the Association for Computational Linguistics: EMNLP 2022

Lifelong learning aims to accumulate knowledge and alleviate catastrophic forgetting when learning tasks sequentially. However, existing lifelong language learning methods only focus on the supervised learning setting. Unlabeled data, which can be easily accessed in real-world scenarios, are underexplored. In this paper, we explore a novel setting, semi-supervised lifelong language learning (SSLL), where a model learns sequentially arriving language tasks with both labeled and unlabeled data. We propose an unlabeled data enhanced lifelong learner to explore SSLL. Specially, we dedicate task-specific modules to alleviate catastrophic forgetting and design two modules to exploit unlabeled data: (1) a virtual supervision enhanced task solver is constructed on a teacher-student framework to mine the underlying knowledge from unlabeled data; and (2) a backward augmented learner is built to encourage knowledge transfer from newly arrived unlabeled data to previous tasks. Experimental results on various language tasks demonstrate our model’s effectiveness and superiority over competitive baselines under the new setting SSLL.

pdf
MMChat: Multi-Modal Chat Dataset on Social Media
Yinhe Zheng | Guanyi Chen | Xin Liu | Jian Sun
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Incorporating multi-modal contexts in conversation is an important step for developing more engaging dialogue systems. In this work, we explore this direction by introducing MMChat: a large scale Chinese multi-modal dialogue corpus (32.4M raw dialogues and 120.84K filtered dialogues). Unlike previous corpora that are crowd-sourced or collected from fictitious movies, MMChat contains image-grounded dialogues collected from real conversations on social media, in which the sparsity issue is observed. Specifically, image-initiated dialogues in common communications may deviate to some non-image-grounded topics as the conversation proceeds. To better investigate this issue, we manually annotate 100K dialogues from MMChat and further filter the corpus accordingly, which yields MMChat-hf. We develop a benchmark model to address the sparsity issue in dialogue generation tasks by adapting the attention routing mechanism on image features. Experiments demonstrate the usefulness of incorporating image features and the effectiveness in handling the sparsity of image features.

pdf
Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Yingxiu Zhao | Zhiliang Tian | Huaxiu Yao | Yinhe Zheng | Dongkyu Lee | Yiping Song | Jian Sun | Nevin Zhang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Building models of natural language processing (NLP) is challenging in low-resource scenarios where limited data are available. Optimization-based meta-learning algorithms achieve promising results in low-resource scenarios by adapting a well-generalized model initialization to handle new tasks. Nonetheless, these approaches suffer from the memorization overfitting issue, where the model tends to memorize the meta-training tasks while ignoring support sets when adapting to new tasks. To address this issue, we propose a memory imitation meta-learning (MemIML) method that enhances the model’s reliance on support sets for task adaptation. Specifically, we introduce a task-specific memory module to store support set information and construct an imitation module to force query sets to imitate the behaviors of support sets stored in the memory. A theoretical analysis is provided to prove the effectiveness of our method, and empirical results also demonstrate that our method outperforms competitive baselines on both text classification and generation tasks.

pdf
Rethinking and Refining the Distinct Metric
Siyang Liu | Sahand Sabour | Yinhe Zheng | Pei Ke | Xiaoyan Zhu | Minlie Huang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Distinct is a widely used automatic metric for evaluating diversity in language generation tasks.However, we observed that the original approach to calculating distinct scores has evident biases that tend to assign higher penalties to longer sequences. We refine the calculation of distinct scores by scaling the number of distinct tokens based on their expectations. We provide both empirical and theoretical evidence to show that our method effectively removes the biases existing in the original distinct score. Our experiments show that our proposed metric, Expectation-Adjusted Distinct (EAD), correlates better with human judgment in evaluating response diversity.To assist future research, we provide an example implementation at https://github.com/lsy641/Expectation-Adjusted-Distinct.

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

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

pdf
Estimating Soft Labels for Out-of-Domain Intent Detection
Hao Lang | Yinhe Zheng | Jian Sun | Fei Huang | Luo Si | Yongbin Li
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these pseudo samples. However, these one-hot labels introduce noises to the training process because some “hard” pseudo OOD samples may coincide with In-Domain (IND) intents. In this paper, we propose an adaptive soft pseudo labeling (ASoul) method that can estimate soft labels for pseudo OOD samples when training OOD detectors. Semantic connections between pseudo OOD samples and IND intents are captured using an embedding graph. A co-training framework is further introduced to produce resulting soft labels following the smoothness assumption, i.e., close samples are likely to have similar labels. Extensive experiments on three benchmark datasets show that ASoul consistently improves the OOD detection performance and outperforms various competitive baselines.

pdf
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
Yingxiu Zhao | Yinhe Zheng | Zhiliang Tian | Chang Gao | Jian Sun | Nevin L. Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems. To address the catastrophic forgetting issue of LL, generative replay methods are widely employed to consolidate past knowledge with generated pseudo samples. However, most existing generative replay methods use only a single task-specific token to control their models. This scheme is usually not strong enough to constrain the generative model due to insufficient information involved. In this paper, we propose a novel method, prompt conditioned VAE for lifelong learning (PCLL), to enhance generative replay by incorporating tasks’ statistics. PCLL captures task-specific distributions with a conditional variational autoencoder, conditioned on natural language prompts to guide the pseudo-sample generation. Moreover, it leverages a distillation process to further consolidate past knowledge by alleviating the noise in pseudo samples. Experiments on natural language understanding tasks of ToD systems demonstrate that PCLL significantly outperforms competitive baselines in building lifelong learning models.

2021

pdf
Transferable Persona-Grounded Dialogues via Grounded Minimal Edits
Chen Henry Wu | Yinhe Zheng | Xiaoxi Mao | Minlie Huang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Grounded dialogue models generate responses that are grounded on certain concepts. Limited by the distribution of grounded dialogue data, models trained on such data face the transferability challenges in terms of the data distribution and the type of grounded concepts. To address the challenges, we propose the grounded minimal editing framework, which minimally edits existing responses to be grounded on the given concept. Focusing on personas, we propose Grounded Minimal Editor (GME), which learns to edit by disentangling and recombining persona-related and persona-agnostic parts of the response. To evaluate persona-grounded minimal editing, we present the PersonaMi-nEdit dataset, and experimental results show that GME outperforms competitive baselines by a large margin. To evaluate the transferability, we experiment on the test set of BlendedSkillTalk and show that GME can edit dialogue models’ responses to largely improve their persona consistency while preserving the use of knowledge and empathy.

pdf
Diversifying Dialog Generation via Adaptive Label Smoothing
Yida Wang | Yinhe Zheng | Yong Jiang | Minlie Huang
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)

Neural dialogue generation models trained with the one-hot target distribution suffer from the over-confidence issue, which leads to poor generation diversity as widely reported in the literature. Although existing approaches such as label smoothing can alleviate this issue, they fail to adapt to diverse dialog contexts. In this paper, we propose an Adaptive Label Smoothing (AdaLabel) approach that can adaptively estimate a target label distribution at each time step for different contexts. The maximum probability in the predicted distribution is used to modify the soft target distribution produced by a novel light-weight bi-directional decoder module. The resulting target distribution is aware of both previous and future contexts and is adjusted to avoid over-training the dialogue model. Our model can be trained in an endto-end manner. Extensive experiments on two benchmark datasets show that our approach outperforms various competitive baselines in producing diverse responses.

2020

pdf
Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data
Rongsheng Zhang | Yinhe Zheng | Jianzhi Shao | Xiaoxi Mao | Yadong Xi | Minlie Huang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data dilemma, we propose a novel data augmentation method for training open-domain dialogue models by utilizing unpaired data. Specifically, a data-level distillation process is first proposed to construct augmented dialogues where both post and response are retrieved from the unpaired data. A ranking module is employed to filter out low-quality dialogues. Further, a model-level distillation process is employed to distill a teacher model trained on high-quality paired data to augmented dialogue pairs, thereby preventing dialogue models from being affected by the noise in the augmented data. Automatic and manual evaluation indicates that our method can produce high-quality dialogue pairs with diverse contents, and the proposed data-level and model-level dialogue distillation can improve the performance of competitive baselines.

pdf
Listener’s Social Identity Matters in Personalised Response Generation
Guanyi Chen | Yinhe Zheng | Yupei Du
Proceedings of the 13th International Conference on Natural Language Generation

Personalised response generation enables generating human-like responses by means of assigning the generator a social identity. However, pragmatics theory suggests that human beings adjust the way of speaking based on not only who they are but also whom they are talking to. In other words, when modelling personalised dialogues, it might be favourable if we also take the listener’s social identity into consideration. To validate this idea, we use gender as a typical example of a social variable to investigate how the listener’s identity influences the language used in Chinese dialogues on social media. Also, we build personalised generators. The experiment results demonstrate that the listener’s identity indeed matters in the language use of responses and that the response generator can capture such differences in language use. More interestingly, by additionally modelling the listener’s identity, the personalised response generator performs better in its own identity.

2018

pdf
Quantifying Context Overlap for Training Word Embeddings
Yimeng Zhuang | Jinghui Xie | Yinhe Zheng | Xuan Zhu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Most models for learning word embeddings are trained based on the context information of words, more precisely first order co-occurrence relations. In this paper, a metric is designed to estimate second order co-occurrence relations based on context overlap. The estimated values are further used as the augmented data to enhance the learning of word embeddings by joint training with existing neural word embedding models. Experimental results show that better word vectors can be obtained for word similarity tasks and some downstream NLP tasks by the enhanced approach.