He-Yan Huang

Also published as: He-yan Huang, Heyan Huang


2023

pdf bib
Boosting Event Extraction with Denoised Structure-to-Text Augmentation
Bo Wang | Heyan Huang | Xiaochi Wei | Ge Shi | Xiao Liu | Chong Feng | Tong Zhou | Shuaiqiang Wang | Dawei Yin
Findings of the Association for Computational Linguistics: ACL 2023

Event extraction aims to recognize pre-defined event triggers and arguments from texts, which suffer from the lack of high-quality annotations. In most NLP applications, involving a large scale of synthetic training data is a practical and effective approach to alleviate the problem of data scarcity. However, when applying to the task of event extraction, recent data augmentation methods often neglect the problem of grammatical incorrectness, structure misalignment, and semantic drifting, leading to unsatisfactory performances. In order to solve these problems, we propose a denoised structure-to-text augmentation framework for event extraction (DAEE), which generates additional training data through the knowledge-based structure-to-text generation model and selects the effective subset from the generated data iteratively with a deep reinforcement learning agent. Experimental results on several datasets demonstrate that the proposed method generates more diverse text representations for event extraction and achieves comparable results with the state-of-the-art.

pdf bib
Can Cross-Lingual Transferability of Multilingual Transformers Be Activated Without End-Task Data?
Zewen Chi | Heyan Huang | Xian-Ling Mao
Findings of the Association for Computational Linguistics: ACL 2023

Pretrained multilingual Transformers have achieved great success in cross-lingual transfer learning. Current methods typically activate the cross-lingual transferability of multilingual Transformers by fine-tuning them on end-task data. However, the methods cannot perform cross-lingual transfer when end-task data are unavailable. In this work, we explore whether the cross-lingual transferability can be activated without end-task data. We propose a cross-lingual transfer method, named PlugIn-X. PlugIn-X disassembles monolingual and multilingual Transformers into sub-modules, and reassembles them to be the multilingual end-task model. After representation adaptation, PlugIn-X finally performs cross-lingual transfer in a plug-and-play style. Experimental results show that PlugIn-X successfully activates the cross-lingual transferability of multilingual Transformers without accessing end-task data. Moreover, we analyze how the cross-model representation alignment affects the cross-lingual transferability.

pdf bib
AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking
Yuxiang Nie | Heyan Huang | Wei Wei | Xian-Ling Mao
Findings of the Association for Computational Linguistics: ACL 2023

Annotating long-document question answering (long-document QA) pairs is time-consuming and expensive. To alleviate the problem, it might be possible to generate long-document QA pairs via unsupervised question answering (UQA) methods. However, existing UQA tasks are based on short documents, and can hardly incorporate long-range information. To tackle the problem, we propose a new task, named unsupervised long-document question answering (ULQA), aiming to generate high-quality long-document QA instances in an unsupervised manner. Besides, we propose AttenWalker, a novel unsupervised method to aggregate and generate answers with long-range dependency so as to construct long-document QA pairs. Specifically, AttenWalker is composed of three modules, i.e. span collector, span linker and answer aggregator. Firstly, the span collector takes advantage of constituent parsing and reconstruction loss to select informative candidate spans for constructing answers. Secondly, with the help of the attention graph of a pre-trained long-document model, potentially interrelated text spans (that might be far apart) could be linked together via an attention-walking algorithm. Thirdly, in the answer aggregator, linked spans are aggregated into the final answer via the mask-filling ability of a pre-trained model. Extensive experiments show that AttenWalker outperforms previous methods on NarrativeQA and Qasper. In addition, AttenWalker also shows strong performance in the few-shot learning setting.

pdf bib
Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue
Yizhe Yang | Heyan Huang | Yuhang Liu | Yang Gao
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Knowledge-grounded dialogue is a task of gener- ating an informative response based on both the dialogue history and external knowledge source. In general, there are two forms of knowledge: manu- ally annotated knowledge graphs and knowledge text from website. From various evaluation viewpoints, each type of knowledge has advantages and downsides. To further distinguish the principles and determinants from the intricate factors, we conduct a thorough experiment and study on the task to answer three essential questions. The ques- tions involve the choice of appropriate knowledge form, the degree of mutual effects between knowl- edge and the model selection, and the few-shot performance of knowledge. Supported by statistical shreds of evidence, we offer conclusive solutions and sensible suggestions for directions and standards of future research.

pdf bib
Towards Faithful Dialogues via Focus Learning
Yifan Deng | Xingsheng Zhang | Heyan Huang | Yue Hu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Maintaining faithfulness between responses and knowledge is an important research topic for building reliable knowledge-grounded dialogue systems. Existing models heavily rely on elaborate data engineering or increasing the model’s parameters ignoring to track the tokens that significantly influence losses, which is decisive for the optimization direction of the model in each iteration. To address this issue, we propose Focus Learning (FocusL), a novel learning approach that adjusts the contribution of each token to the optimization direction by directly scaling the corresponding objective loss. Specifically, we first introduce a positioning method by utilizing similarity distributions between knowledge and each response token to locate knowledge-aware tokens. Then, we further design a similarity-to-weight transformation to provide dynamic token-level weights for the cross-entropy loss. Finally, we use the weighted loss to encourage the model to pay special attention to the knowledge utilization. Experimental results demonstrate that our method achieves the new state-of-the-art results and generates more reliable responses while maintaining training stability.

pdf bib
TemplateGEC: Improving Grammatical Error Correction with Detection Template
Yinghao Li | Xuebo Liu | Shuo Wang | Peiyuan Gong | Derek F. Wong | Yang Gao | Heyan Huang | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Grammatical error correction (GEC) can be divided into sequence-to-edit (Seq2Edit) and sequence-to-sequence (Seq2Seq) frameworks, both of which have their pros and cons. To utilize the strengths and make up for the shortcomings of these frameworks, this paper proposes a novel method, TemplateGEC, which capitalizes on the capabilities of both Seq2Edit and Seq2Seq frameworks in error detection and correction respectively. TemplateGEC utilizes the detection labels from a Seq2Edit model, to construct the template as the input. A Seq2Seq model is employed to enforce consistency between the predictions of different templates by utilizing consistency learning. Experimental results on the Chinese NLPCC18, English BEA19 and CoNLL14 benchmarks show the effectiveness and robustness of TemplateGEC.Further analysis reveals the potential of our method in performing human-in-the-loop GEC. Source code and scripts are available at https://github.com/li-aolong/TemplateGEC.

pdf bib
Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension
Xiao Zhang | Heyan Huang | Zewen Chi | Xian-Ling Mao
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of “Yes/No/Inquire” or generate a follow-up question when the decision is “Inquire” based on retrieved rule texts, user scenario, user question and dialogue history. Recent studies try to reduce the information gap between decision-making and question generation, in order to improve the performance of generation. However, the information gap still persists because these methods are still limited in pipeline framework, where decision-making and question generation are performed separately, making it hard to share the entailment reasoning used in decision-making across all stages. To tackle the above problem, we propose a novel one-stage end-to-end framework, called Entailment Fused-T5 (EFT), to bridge the information gap between decision-making and question generation in a global understanding manner. The extensive experimental results demonstrate that our proposed framework achieves new state-of-the-art performance on the OR-ShARC benchmark. Our model and code are publicly available at an anonymous link.

pdf bib
Discriminative Reasoning with Sparse Event Representation for Document-level Event-Event Relation Extraction
Changsen Yuan | Heyan Huang | Yixin Cao | Yonggang Wen
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Document-level Event Causality Identification (DECI) aims to extract causal relations between events in a document. It challenges conventional sentence-level task (SECI) with difficult long-text understanding. In this paper, we propose a novel DECI model (SENDIR) for better document-level reasoning. Different from existing works that build an event graph via linguistic tools, SENDIR does not require any prior knowledge. The basic idea is to discriminate event pairs in the same sentence or span multiple sentences by assuming their different information density: 1) low density in the document suggests sparse attention to skip irrelevant information. Our module 1 designs various types of attention for event representation learning to capture long-distance dependence. 2) High density in a sentence makes SECI relatively easy. Module 2 uses different weights to highlight the roles and contributions of intra- and inter-sentential reasoning, which introduces supportive event pairs for joint modeling. Extensive experiments demonstrate great improvements in SENDIR and the effectiveness of various sparse attention for document-level representations. Codes will be released later.

2022

pdf bib
Cross-Lingual Phrase Retrieval
Heqi Zheng | Xiao Zhang | Zewen Chi | Heyan Huang | Yan Tan | Tian Lan | Wei Wei | Xian-Ling Mao
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, how to learn phrase representations for cross-lingual phrase retrieval is still an open problem. In this paper, we propose , a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences. Moreover, we create a large-scale cross-lingual phrase retrieval dataset, which contains 65K bilingual phrase pairs and 4.2M example sentences in 8 English-centric language pairs. Experimental results show that outperforms state-of-the-art baselines which utilize word-level or sentence-level representations. also shows impressive zero-shot transferability that enables the model to perform retrieval in an unseen language pair during training. Our dataset, code, and trained models are publicly available at github.com/cwszz/XPR/.

pdf bib
Dynamic Prefix-Tuning for Generative Template-based Event Extraction
Xiao Liu | Heyan Huang | Ge Shi | Bo Wang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We consider event extraction in a generative manner with template-based conditional generation. Although there is a rising trend of casting the task of event extraction as a sequence generation problem with prompts, these generation-based methods have two significant challenges, including using suboptimal prompts and static event type information. In this paper, we propose a generative template-based event extraction method with dynamic prefix (GTEE-DynPref) by integrating context information with type-specific prefixes to learn a context-specific prefix for each context. Experimental results show that our model achieves competitive results with the state-of-the-art classification-based model OneIE on ACE 2005 and achieves the best performances on ERE.Additionally, our model is proven to be portable to new types of events effectively.

pdf bib
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 bib
ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension
Xiao Zhang | Heyan Huang | Zewen Chi | Xian-Ling Mao
Proceedings of the 29th International Conference on Computational Linguistics

Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. Existing methods typically require three steps: (1) decision making based on entailment reasoning; (2) span extraction if required by the above decision; (3) question rephrasing based on the extracted span. However, for nearly all these methods, the span extraction and question rephrasing steps cannot fully exploit the fine-grained entailment reasoning information in decision making step because of their relative independence, which will further enlarge the information gap between decision making and question phrasing. Thus, to tackle this problem, we propose a novel end-to-end framework for conversational machine reading comprehension based on shared parameter mechanism, called entailment reasoning T5 (ET5). Despite the lightweight of our proposed framework, experimental results show that the proposed ET5 achieves new state-of-the-art results on the ShARC leaderboard with the BLEU-4 score of 55.2. Our model and code are publicly available.

pdf bib
Unsupervised Question Answering via Answer Diversifying
Yuxiang Nie | Heyan Huang | Zewen Chi | Xian-Ling Mao
Proceedings of the 29th International Conference on Computational Linguistics

Unsupervised question answering is an attractive task due to its independence on labeled data. Previous works usually make use of heuristic rules as well as pre-trained models to construct data and train QA models. However, most of these works regard named entity (NE) as the only answer type, which ignores the high diversity of answers in the real world. To tackle this problem, we propose a novel unsupervised method by diversifying answers, named DiverseQA. Specifically, the proposed method is composed of three modules: data construction, data augmentation and denoising filter. Firstly, the data construction module extends the extracted named entity into a longer sentence constituent as the new answer span to construct a QA dataset with diverse answers. Secondly, the data augmentation module adopts an answer-type dependent data augmentation process via adversarial training in the embedding level. Thirdly, the denoising filter module is designed to alleviate the noise in the constructed data. Extensive experiments show that the proposed method outperforms previous unsupervised models on five benchmark datasets, including SQuADv1.1, NewsQA, TriviaQA, BioASQ, and DuoRC. Besides, the proposed method shows strong performance in the few-shot learning setting.

pdf bib
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Xiaochen Liu | Yang Gao | Yu Bai | Jiawei Li | Yinan Hu | Heyan Huang | Boxing Chen
Proceedings of the 29th International Conference on Computational Linguistics

Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we developed a novel soft prompts architecture coupled with a prompt pre-training plus prompt fine-tuning paradigm, which is effective and tunes only extremely light parameters. To meet the structure of the generation models, the soft prompts comprise continuous input embeddings across an encoder and a decoder. Importantly, a new inner-prompt placed in the text is introduced to capture document-level information. The aim is to devote attention to understanding the document that better prompts the model to generate document-related content. In the training process, the prompt pre-training with self-supervised pseudo-data firstly teaches the model basic summarizing capability. Then, with few-shot examples, only the designed lightweight soft prompts are fine-tuned. Experimental results on the CNN/DailyMail and XSum datasets show that our method, with only 0.1% of the parameters, outperforms full-model tuning where all model parameters are tuned. It also surpasses Prompt Tuning by a large margin and delivers competitive results against Prefix-Tuning with 3% of the parameters.

pdf bib
Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network
Yuxiang Nie | Heyan Huang | Wei Wei | Xian-Ling Mao
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Long document question answering is a challenging task due to its demands for complex reasoning over long text. Previous works usually take long documents as non-structured flat texts or only consider the local structure in long documents. However, these methods usually ignore the global structure of the long document, which is essential for long-range understanding. To tackle this problem, we propose Compressive Graph Selector Network (CGSN) to capture the global structure in a compressive and iterative manner. The proposed model mainly focuses on the evidence selection phase of long document question answering. Specifically, it consists of three modules: local graph network, global graph network and evidence memory network. Firstly, the local graph network builds the graph structure of the chunked segment in token, sentence, paragraph and segment levels to capture the short-term dependency of the text. Secondly, the global graph network selectively receives the information of each level from the local graph, compresses them into the global graph nodes and applies graph attention to the global graph nodes to build the long-range reasoning over the entire text in an iterative way. Thirdly, the evidence memory network is designed to alleviate the redundancy problem in the evidence selection by saving the selected result in the previous steps. Extensive experiments show that the proposed model outperforms previous methods on two datasets.

pdf bib
Revisiting Grammatical Error Correction Evaluation and Beyond
Peiyuan Gong | Xuebo Liu | Heyan Huang | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Pretraining-based (PT-based) automatic evaluation metrics (e.g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e.g., machine translation and text summarization) due to their better correlation with human judgments over traditional overlap-based methods. Although PT-based methods have become the de facto standard for training grammatical error correction (GEC) systems, GEC evaluation still does not benefit from pretrained knowledge. This paper takes the first step towards understanding and improving GEC evaluation with pretraining. We first find that arbitrarily applying PT-based metrics to GEC evaluation brings unsatisfactory correlation results because of the excessive attention to inessential systems outputs (e.g., unchanged parts). To alleviate the limitation, we propose a novel GEC evaluation metric to achieve the best of both worlds, namely PT-M2 which only uses PT-based metrics to score those corrected parts. Experimental results on the CoNLL14 evaluation task show that PT-M2 significantly outperforms existing methods, achieving a new state-of-the-art result of 0.949 Pearson correlation. Further analysis reveals that PT-M2 is robust to evaluate competitive GEC systems. Source code and scripts are freely available at https://github.com/pygongnlp/PT-M2.

2021

pdf bib
Prediction or Comparison: Toward Interpretable Qualitative Reasoning
Mucheng Ren | Heyan Huang | Yang Gao
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
Heng-Da Xu | Zhongli Li | Qingyu Zhou | Chao Li | Zizhen Wang | Yunbo Cao | Heyan Huang | Xian-Ling Mao
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Hashing based Efficient Inference for Image-Text Matching
Rong-Cheng Tu | Lei Ji | Huaishao Luo | Botian Shi | Heyan Huang | Nan Duan | Xian-Ling Mao
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
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 bib
Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation
Tianfu Zhang | Heyan Huang | Chong Feng | Longbing Cao
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Multi-head self-attention recently attracts enormous interest owing to its specialized functions, significant parallelizable computation, and flexible extensibility. However, very recent empirical studies show that some self-attention heads make little contribution and can be pruned as redundant heads. This work takes a novel perspective of identifying and then vitalizing redundant heads. We propose a redundant head enlivening (RHE) method to precisely identify redundant heads, and then vitalize their potential by learning syntactic relations and prior knowledge in the text without sacrificing the roles of important heads. Two novel syntax-enhanced attention (SEA) mechanisms: a dependency mask bias and a relative local-phrasal position bias, are introduced to revise self-attention distributions for syntactic enhancement in machine translation. The importance of individual heads is dynamically evaluated during the redundant heads identification, on which we apply SEA to vitalize redundant heads while maintaining the strength of important heads. Experimental results on widely adopted WMT14 and WMT16 English to German and English to Czech language machine translation validate the RHE effectiveness.

pdf bib
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 bib
Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?
Puhai Yang | Heyan Huang | Xian-Ling Mao
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)

Dialogue state tracking (DST) plays a key role in task-oriented dialogue systems to monitor the user’s goal. In general, there are two strategies to track a dialogue state: predicting it from scratch and updating it from previous state. The scratch-based strategy obtains each slot value by inquiring all the dialogue history, and the previous-based strategy relies on the current turn dialogue to update the previous dialogue state. However, it is hard for the scratch-based strategy to correctly track short-dependency dialogue state because of noise; meanwhile, the previous-based strategy is not very useful for long-dependency dialogue state tracking. Obviously, it plays different roles for the context information of different granularity to track different kinds of dialogue states. Thus, in this paper, we will study and discuss how the context information of different granularity affects dialogue state tracking. First, we explore how greatly different granularities affect dialogue state tracking. Then, we further discuss how to combine multiple granularities for dialogue state tracking. Finally, we apply the findings about context granularity to few-shot learning scenario. Besides, we have publicly released all codes.

pdf bib
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 bib
Cross-Lingual Abstractive Summarization with Limited Parallel Resources
Yu Bai | Yang Gao | Heyan 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)

Parallel cross-lingual summarization data is scarce, requiring models to better use the limited available cross-lingual resources. Existing methods to do so often adopt sequence-to-sequence networks with multi-task frameworks. Such approaches apply multiple decoders, each of which is utilized for a specific task. However, these independent decoders share no parameters, hence fail to capture the relationships between the discrete phrases of summaries in different languages, breaking the connections in order to transfer the knowledge of the high-resource languages to low-resource languages. To bridge these connections, we propose a novel Multi-Task framework for Cross-Lingual Abstractive Summarization (MCLAS) in a low-resource setting. Employing one unified decoder to generate the sequential concatenation of monolingual and cross-lingual summaries, MCLAS makes the monolingual summarization task a prerequisite of the CLS task. In this way, the shared decoder learns interactions involving alignments and summary patterns across languages, which encourages attaining knowledge transfer. Experiments on two CLS datasets demonstrate that our model significantly outperforms three baseline models in both low-resource and full-dataset scenarios. Moreover, in-depth analysis on the generated summaries and attention heads verifies that interactions are learned well using MCLAS, which benefits the CLS task under limited parallel resources.

2020

pdf bib
Towards Interpretable Reasoning over Paragraph Effects in Situation
Mucheng Ren | Xiubo Geng | Tao Qin | Heyan Huang | Daxin Jiang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing works ignore the complicated reasoning process and solve it with a one-step “black box” model. Inspired by human cognitive processes, in this paper we propose a sequential approach for this task which explicitly models each step of the reasoning process with neural network modules. In particular, five reasoning modules are designed and learned in an end-to-end manner, which leads to a more interpretable model. Experimental results on the ROPES dataset demonstrate the effectiveness and explainability of our proposed approach.

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 bib
Weibo-COV: A Large-Scale COVID-19 Social Media Dataset from Weibo
Yong Hu | Heyan Huang | Anfan Chen | Xian-Ling Mao
Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020

With the rapid development of COVID-19 around the world, people are requested to maintain “social distance” and “stay at home”. In this scenario, extensive social interactions transfer to cyberspace, especially on social media platforms like Twitter and Sina Weibo. People generate posts to share information, express opinions and seek help during the pandemic outbreak, and these kinds of data on social media are valuable for studies to prevent COVID-19 transmissions, such as early warning and outbreaks detection. Therefore, in this paper, we release a novel and fine-grained large-scale COVID-19 social media dataset collected from Sina Weibo, named Weibo-COV, contains more than 40 million posts ranging from December 1, 2019 to April 30, 2020. Moreover, this dataset includes comprehensive information nuggets like post-level information, interactive information, location information, and repost network. We hope this dataset can promote studies of COVID-19 from multiple perspectives and enable better and rapid researches to suppress the spread of this pandemic.

2019

pdf bib
Open Domain Event Extraction Using Neural Latent Variable Models
Xiao Liu | Heyan Huang | Yue Zhang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters. A novel latent variable neural model is constructed, which is scalable to very large corpus. A dataset is collected and manually annotated, with task-specific evaluation metrics being designed. Results show that the proposed unsupervised model gives better performance compared to the state-of-the-art method for event schema induction.

pdf bib
Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning
Xuewen Shi | Heyan Huang | Wenguan Wang | Ping Jian | Yi-Kun Tang
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

Neural Machine Translation (NMT) optimized by Maximum Likelihood Estimation (MLE) lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge learned from bilingual sentence alignment. Specifically, we first design a discriminator that learns to estimate sentence aligning score over translation candidates, and then the learned semantic knowledge is transfered to the NMT model under an adversarial learning framework. We also propose a gated self-attention based encoder for sentence embedding. Furthermore, an N-pair training loss is introduced in our framework to aid the discriminator in better capturing lexical evidence in translation candidates. Experimental results show that our proposed method outperforms baseline NMT models on Chinese-to-English and English-to-German translation tasks. Further analysis also indicates the detailed semantic knowledge transfered from the discriminator to the NMT model.

pdf bib
Concept Pointer Network for Abstractive Summarization
Wenbo Wang | Yang Gao | Heyan Huang | Yuxiang Zhou
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

A quality abstractive summary should not only copy salient source texts as summaries but should also tend to generate new conceptual words to express concrete details. Inspired by the popular pointer generator sequence-to-sequence model, this paper presents a concept pointer network for improving these aspects of abstractive summarization. The network leverages knowledge-based, context-aware conceptualizations to derive an extended set of candidate concepts. The model then points to the most appropriate choice using both the concept set and original source text. This joint approach generates abstractive summaries with higher-level semantic concepts. The training model is also optimized in a way that adapts to different data, which is based on a novel method of distant-supervised learning guided by reference summaries and testing set. Overall, the proposed approach provides statistically significant improvements over several state-of-the-art models on both the DUC-2004 and Gigaword datasets. A human evaluation of the model’s abstractive abilities also supports the quality of the summaries produced within this framework.

2018

pdf bib
Task-oriented Word Embedding for Text Classification
Qian Liu | Heyan Huang | Yang Gao | Xiaochi Wei | Yuxin Tian | Luyang Liu
Proceedings of the 27th International Conference on Computational Linguistics

Distributed word representation plays a pivotal role in various natural language processing tasks. In spite of its success, most existing methods only consider contextual information, which is suboptimal when used in various tasks due to a lack of task-specific features. The rational word embeddings should have the ability to capture both the semantic features and task-specific features of words. In this paper, we propose a task-oriented word embedding method and apply it to the text classification task. With the function-aware component, our method regularizes the distribution of words to enable the embedding space to have a clear classification boundary. We evaluate our method using five text classification datasets. The experiment results show that our method significantly outperforms the state-of-the-art methods.

pdf bib
Zewen at SemEval-2018 Task 1: An Ensemble Model for Affect Prediction in Tweets
Zewen Chi | Heyan Huang | Jiangui Chen | Hao Wu | Ran Wei
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper presents a method for Affect in Tweets, which is the task to automatically determine the intensity of emotions and intensity of sentiment of tweets. The term affect refers to emotion-related categories such as anger, fear, etc. Intensity of emo-tions need to be quantified into a real valued score in [0, 1]. We propose an en-semble system including four different deep learning methods which are CNN, Bidirectional LSTM (BLSTM), LSTM-CNN and a CNN-based Attention model (CA). Our system gets an average Pearson correlation score of 0.682 in the subtask EI-reg and an average Pearson correlation score of 0.784 in subtask V-reg, which ranks 17th among 48 systems in EI-reg and 19th among 38 systems in V-reg.

pdf bib
Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction
Ge Shi | Chong Feng | Lifu Huang | Boliang Zhang | Heng Ji | Lejian Liao | Heyan Huang
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions. Previous studies address this problem by discovering a shared space across genres using manually crafted features, which requires great human effort. To effectively automate this process, we design a genre-separation network, which applies two encoders, one genre-independent and one genre-shared, to explicitly extract genre-specific and genre-agnostic features. Then we train a relation classifier using the genre-agnostic features on the source genre and directly apply to the target genre. Experiment results on three distinct genres of the ACE dataset show that our approach achieves up to 6.1% absolute F1-score gain compared to previous methods. By incorporating a set of external linguistic features, our approach outperforms the state-of-the-art by 1.7% absolute F1 gain. We make all programs of our model publicly available for research purpose

pdf bib
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
Xiao Liu | Zhunchen Luo | Heyan Huang
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Event extraction is of practical utility in natural language processing. In the real world, it is a common phenomenon that multiple events existing in the same sentence, where extracting them are more difficult than extracting a single event. Previous works on modeling the associations between events by sequential modeling methods suffer a lot from the low efficiency in capturing very long-range dependencies. In this paper, we propose a novel Jointly Multiple Events Extraction (JMEE) framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information. The experiment results demonstrate that our proposed framework achieves competitive results compared with state-of-the-art methods.

2017

pdf bib
BIT at SemEval-2017 Task 1: Using Semantic Information Space to Evaluate Semantic Textual Similarity
Hao Wu | Heyan Huang | Ping Jian | Yuhang Guo | Chao Su
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

This paper presents three systems for semantic textual similarity (STS) evaluation at SemEval-2017 STS task. One is an unsupervised system and the other two are supervised systems which simply employ the unsupervised one. All our systems mainly depend on the (SIS), which is constructed based on the semantic hierarchical taxonomy in WordNet, to compute non-overlapping information content (IC) of sentences. Our team ranked 2nd among 31 participating teams by the primary score of Pearson correlation coefficient (PCC) mean of 7 tracks and achieved the best performance on Track 1 (AR-AR) dataset.

pdf bib
QLUT at SemEval-2017 Task 2: Word Similarity Based on Word Embedding and Knowledge Base
Fanqing Meng | Wenpeng Lu | Yuteng Zhang | Ping Jian | Shumin Shi | Heyan Huang
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

This paper shows the details of our system submissions in the task 2 of SemEval 2017. We take part in the subtask 1 of this task, which is an English monolingual subtask. This task is designed to evaluate the semantic word similarity of two linguistic items. The results of runs are assessed by standard Pearson and Spearman correlation, contrast with official gold standard set. The best performance of our runs is 0.781 (Final). The techniques of our runs mainly make use of the word embeddings and the knowledge-based method. The results demonstrate that the combined method is effective for the computation of word similarity, while the word embeddings and the knowledge-based technique, respectively, needs more deeply improvement in details.

pdf bib
A Parallel Recurrent Neural Network for Language Modeling with POS Tags
Chao Su | Heyan Huang | Shumin Shi | Yuhang Guo | Hao Wu
Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation

2016

pdf bib
BIT at SemEval-2016 Task 1: Sentence Similarity Based on Alignments and Vector with the Weight of Information Content
Hao Wu | Heyan Huang | Wenpeng Lu
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

pdf bib
CSE: Conceptual Sentence Embeddings based on Attention Model
Yashen Wang | Heyan Huang | Chong Feng | Qiang Zhou | Jiahui Gu | Xiong Gao
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
A Novel Fast Framework for Topic Labeling Based on Similarity-preserved Hashing
Xian-Ling Mao | Yi-Jing Hao | Qiang Zhou | Wen-Qing Yuan | Liner Yang | Heyan Huang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Recently, topic modeling has been widely applied in data mining due to its powerful ability. A common, major challenge in applying such topic models to other tasks is to accurately interpret the meaning of each topic. Topic labeling, as a major interpreting method, has attracted significant attention recently. However, most of previous works only focus on the effectiveness of topic labeling, and less attention has been paid to quickly creating good topic descriptors; meanwhile, it’s hard to assign labels for new emerging topics by using most of existing methods. To solve the problems above, in this paper, we propose a novel fast topic labeling framework that casts the labeling problem as a k-nearest neighbor (KNN) search problem in a probability vector set. Our experimental results show that the proposed sequential interleaving method based on locality sensitive hashing (LSH) technology is efficient in boosting the comparison speed among probability distributions, and the proposed framework can generate meaningful labels to interpret topics, including new emerging topics.

2015

pdf bib
Topic-Based Chinese Message Polarity Classification System at SIGHAN8-Task2
Chun Liao | Chong Feng | Sen Yang | Heyan Huang
Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing

2014

pdf bib
Introduction to BIT Chinese Spelling Correction System at CLP 2014 Bake-off
Min Liu | Ping Jian | Heyan Huang
Proceedings of the Third CIPS-SIGHAN Joint Conference on Chinese Language Processing

2012

pdf bib
Chinese Word Sense Disambiguation based on Context Expansion
Zhizhuo Yang | Heyan Huang
Proceedings of COLING 2012: Posters

pdf bib
Emotional Tendency Identification for Micro-blog Topics Based on Multiple Characteristics
Quanchao Liu | Chong Feng | Heyan Huang
Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation

2011

pdf bib
Unsupervised Word Sense Disambiguation Using Neighborhood Knowledge
Heyan Huang | Zhizhuo Yang | Ping Jian
Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation

pdf bib
An English-Chinese Cross-lingual Word Semantic Similarity Measure Exploring Attributes and Relations
Lin Dai | Heyan Huang
Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation

2010

pdf bib
Incorporating New Words Detection with Chinese Word Segmentation
Hua-Ping Zhang | Jian Gao | Qian Mo | He-Yan Huang
CIPS-SIGHAN Joint Conference on Chinese Language Processing

pdf bib
Chinese Personal Name Disambiguation Based on Person Modeling
Hua-Ping Zhang | Zhi-Hua Liu | Qian Mo | He-Yan Huang
CIPS-SIGHAN Joint Conference on Chinese Language Processing

2008

pdf bib
Applications of MT during Olympic Games 2008
Chengqing Zong | Heyan Huang | Shuming Shi
Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Government and Commercial Uses of MT

2006

pdf bib
Translation & Transform Algorithm of Query Sentence in Cross-Language Information Retrieval
Xiao-fei Zhang | Ke-liang Zhang | He-yan Huang
Proceedings of the 20th Pacific Asia Conference on Language, Information and Computation

Search