Shizhu He


2022

pdf bib
Incremental Intent Detection for Medical Domain with Contrast Replay Networks
Guirong Bai | Shizhu He | Kang Liu | Jun Zhao
Findings of the Association for Computational Linguistics: ACL 2022

Conventional approaches to medical intent detection require fixed pre-defined intent categories. However, due to the incessant emergence of new medical intents in the real world, such requirement is not practical. Considering that it is computationally expensive to store and re-train the whole data every time new data and intents come in, we propose to incrementally learn emerged intents while avoiding catastrophically forgetting old intents. We first formulate incremental learning for medical intent detection. Then, we employ a memory-based method to handle incremental learning. We further propose to enhance the method with contrast replay networks, which use multilevel distillation and contrast objective to address training data imbalance and medical rare words respectively. Experiments show that the proposed method outperforms the state-of-the-art model by 5.7% and 9.1% of accuracy on two benchmarks respectively.

pdf bib
Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder
Fangyu Lei | Shizhu He | Xiang Li | Jun Zhao | Kang Liu
Proceedings of the 29th International Conference on Computational Linguistics

pdf bib
Decoupling Mixture-of-Graphs: Unseen Relational Learning for Knowledge Graph Completion by Fusing Ontology and Textual Experts
Ran Song | Shizhu He | Suncong Zheng | Shengxiang Gao | Kang Liu | Zhengtao Yu | Jun Zhao
Proceedings of the 29th International Conference on Computational Linguistics

Knowledge Graph Embedding (KGE) has been proposed and successfully utilized to knowledge Graph Completion (KGC). But classic KGE paradigm often fail in unseen relation representations. Previous studies mainly utilize the textual descriptions of relations and its neighbor relations to represent unseen relations. In fact, the semantics of a relation can be expressed by three kinds of graphs: factual graph, ontology graph, textual description graph, and they can complement each other. A more common scenario in the real world is that seen and unseen relations appear at the same time. In this setting, the training set (only seen relations) and testing set (both seen and unseen relations) own different distributions. And the train-test inconsistency problem will make KGE methods easiy overfit on seen relations and under-performance on unseen relations. In this paper, we propose decoupling mixture-of-graph experts (DMoG) for unseen relations learning, which could represent the unseen relations in the factual graph by fusing ontology and textual graphs, and decouple fusing space and reasoning space to alleviate overfitting for seen relations. The experiments on two unseen only public datasets and a mixture dataset verify the effectiveness of the proposed method, which improves the state-of-the-art methods by 6.84% in Hits@10 on average.

pdf bib
LingJing at SemEval-2022 Task 1: Multi-task Self-supervised Pre-training for Multilingual Reverse Dictionary
Bin Li | Yixuan Weng | Fei Xia | Shizhu He | Bin Sun | Shutao Li
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper introduces the approach of Team LingJing’s experiments on SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings (CODWOE). This task aims at comparing two types of semantic descriptions and including two sub-tasks: the definition modeling and reverse dictionary track. Our team focuses on the reverse dictionary track and adopts the multi-task self-supervised pre-training for multilingual reverse dictionaries. Specifically, the randomly initialized mDeBERTa-base model is used to perform multi-task pre-training on the multilingual training datasets. The pre-training step is divided into two stages, namely the MLM pre-training stage and the contrastive pre-training stage. The experimental results show that the proposed method has achieved good performance in the reverse dictionary track, where we rank the 1-st in the Sgns targets of the EN and RU languages. All the experimental codes are open-sourced at https://github.com/WENGSYX/Semeval.

pdf bib
LingJing at SemEval-2022 Task 3: Applying DeBERTa to Lexical-level Presupposed Relation Taxonomy with Knowledge Transfer
Fei Xia | Bin Li | Yixuan Weng | Shizhu He | Bin Sun | Shutao Li | Kang Liu | Jun Zhao
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper presents the results and main findings of our system on SemEval-2022 Task 3 Presupposed Taxonomies: Evaluating Neural Network Semantics (PreTENS). This task aims at semantic competence with specific attention on the evaluation of language models, which is a task with respect to the recognition of appropriate taxonomic relations between two nominal arguments. Two sub-tasks including binary classification and regression are designed for the evaluation. For the classification sub-task, we adopt the DeBERTa-v3 pre-trained model for fine-tuning datasets of different languages. Due to the small size of the training datasets of the regression sub-task, we transfer the knowledge of classification model (i.e., model parameters) to the regression task. The experimental results show that the proposed method achieves the best results on both sub-tasks. Meanwhile, we also report negative results of multiple training strategies for further discussion. All the experimental codes are open-sourced at https://github.com/WENGSYX/Semeval.

pdf bib
Knowledge Transfer with Visual Prompt in multi-modal Dialogue Understanding and Generation
Minjun Zhu | Yixuan Weng | Bin Li | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the First Workshop On Transcript Understanding

Visual Dialogue (VD) task has recently received increasing attention in AI research. Visual Dialog aims to generate multi-round, interactive responses based on the dialog history and image content. Existing textual dialogue models cannot fully understand visual information, resulting in a lack of scene features when communicating with humans continuously. Therefore, how to efficiently fuse multimodal data features remains to be a challenge. In this work, we propose a knowledge transfer method with visual prompt (VPTG) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle visual dialogue tasks. The VPTG conducts text-image co-learning and multi-modal information fusion with visual prompts and visual knowledge distillation. Specifically, we construct visual prompts from visual representations and then induce sequence-to-sequence(seq2seq) models to fuse visual information and textual contexts by visual-text patterns. And we also realize visual knowledge transfer through distillation between two different models’ text representations, so that the seq2seq model can actively learn visual semantic representations. Extensive experiments on the multi-modal dialogue understanding and generation (MDUG) datasets show the proposed VPTG outperforms other single-modal methods, which demonstrate the effectiveness of visual prompt and visual knowledge transfer.

pdf bib
Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing
Runxin Sun | Shizhu He | Chong Zhu | Yaohan He | Jinlong Li | Jun Zhao | Kang Liu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Text-to-SQL aims to parse natural language questions into SQL queries, which is valuable in providing an easy interface to access large databases. Previous work has observed that leveraging lexico-logical alignments is very helpful to improve parsing performance. However, current attention-based approaches can only model such alignments at the token level and have unsatisfactory generalization capability. In this paper, we propose a new approach to leveraging explicit lexico-logical alignments. It first identifies possible phrase-level alignments and injects them as additional contexts to guide the parsing procedure. Experimental results on \textsc{Squall} show that our approach can make better use of such alignments and obtains an absolute improvement of 3.4% compared with the current state-of-the-art.

2021

pdf bib
Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks
Qingbin Liu | Pengfei Cao | Cao Liu | Jiansong Chen | Xunliang Cai | Fan Yang | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Dialogue state tracking (DST), which estimates user goals given a dialogue context, is an essential component of task-oriented dialogue systems. Conventional DST models are usually trained offline, which requires a fixed dataset prepared in advance. This paradigm is often impractical in real-world applications since online dialogue systems usually involve continually emerging new data and domains. Therefore, this paper explores Domain-Lifelong Learning for Dialogue State Tracking (DLL-DST), which aims to continually train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains. To this end, we propose a novel domain-lifelong learning method, called Knowledge Preservation Networks (KPN), which consists of multi-prototype enhanced retrospection and multi-strategy knowledge distillation, to solve the problems of expression diversity and combinatorial explosion in the DLL-DST task. Experimental results show that KPN effectively alleviates catastrophic forgetting and outperforms previous state-of-the-art lifelong learning methods by 4.25% and 8.27% of whole joint goal accuracy on the MultiWOZ benchmark and the SGD benchmark, respectively.

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

2020

pdf bib
Pre-trained Language Model Based Active Learning for Sentence Matching
Guirong Bai | Shizhu He | Kang Liu | Jun Zhao | Zaiqing Nie
Proceedings of the 28th International Conference on Computational Linguistics

Active learning is able to significantly reduce the annotation cost for data-driven techniques. However, previous active learning approaches for natural language processing mainly depend on the entropy-based uncertainty criterion, and ignore the characteristics of natural language. In this paper, we propose a pre-trained language model based active learning approach for sentence matching. Differing from previous active learning, it can provide linguistic criteria from the pre-trained language model to measure instances and help select more effective instances for annotation. Experiments demonstrate our approach can achieve greater accuracy with fewer labeled training instances.

2019

pdf bib
Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning
Xiangrong Zeng | Shizhu He | Daojian Zeng | Kang Liu | Shengping Liu | Jun Zhao
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

The multiple relation extraction task tries to extract all relational facts from a sentence. Existing works didn’t consider the extraction order of relational facts in a sentence. In this paper we argue that the extraction order is important in this task. To take the extraction order into consideration, we apply the reinforcement learning into a sequence-to-sequence model. The proposed model could generate relational facts freely. Widely conducted experiments on two public datasets demonstrate the efficacy of the proposed method.

pdf bib
Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss
Cao Liu | Kang Liu | Shizhu He | Zaiqing Nie | Jun Zhao
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to be definitive. In this paper, we strive toward the above two issues via incorporating diversified contexts and answer-aware loss. Specifically, we propose a neural encoder-decoder model with multi-level copy mechanisms to generate such questions. Furthermore, the answer aware loss is introduced to make generated questions corresponding to more definitive answers. Experiments demonstrate that our model achieves state-of-the-art performance. Meanwhile, such generated question is able to express the given predicate and correspond to a definitive answer.

pdf bib
Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation
Cao Liu | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We study the task of response generation. Conventional methods employ a fixed vocabulary and one-pass decoding, which not only make them prone to safe and general responses but also lack further refining to the first generated raw sequence. To tackle the above two problems, we present a Vocabulary Pyramid Network (VPN) which is able to incorporate multi-pass encoding and decoding with multi-level vocabularies into response generation. Specifically, the dialogue input and output are represented by multi-level vocabularies which are obtained from hierarchical clustering of raw words. Then, multi-pass encoding and decoding are conducted on the multi-level vocabularies. Since VPN is able to leverage rich encoding and decoding information with multi-level vocabularies, it has the potential to generate better responses. Experiments on English Twitter and Chinese Weibo datasets demonstrate that VPN remarkably outperforms strong baselines.

pdf bib
AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing
Xiang Zhang | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Neural semantic parsers utilize the encoder-decoder framework to learn an end-to-end model for semantic parsing that transduces a natural language sentence to the formal semantic representation. To keep the model aware of the underlying grammar in target sequences, many constrained decoders were devised in a multi-stage paradigm, which decode to the sketches or abstract syntax trees first, and then decode to target semantic tokens. We instead to propose an adaptive decoding method to avoid such intermediate representations. The decoder is guided by model uncertainty and automatically uses deeper computations when necessary. Thus it can predict tokens adaptively. Our model outperforms the state-of-the-art neural models and does not need any expertise like predefined grammar or sketches in the meantime.

pdf bib
Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots
Cao Liu | Kang Liu | Shizhu He | Zaiqing Nie | Jun Zhao
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

Conventional chatbots focus on two-party response generation, which simplifies the real dialogue scene. In this paper, we strive toward a novel task of Response Generation on Multi-Party Chatbot (RGMPC), where the generated responses heavily rely on the interlocutors’ roles (e.g., speaker and addressee) and their utterances. Unfortunately, complex interactions among the interlocutors’ roles make it challenging to precisely capture conversational contexts and interlocutors’ information. Facing this challenge, we present a response generation model which incorporates Interlocutor-aware Contexts into Recurrent Encoder-Decoder frameworks (ICRED) for RGMPC. Specifically, we employ interactive representations to capture dialogue contexts for different interlocutors. Moreover, we leverage an addressee memory to enhance contextual interlocutor information for the target addressee. Finally, we construct a corpus for RGMPC based on an existing open-access dataset. Automatic and manual evaluations demonstrate that the ICRED remarkably outperforms strong baselines.

2018

pdf bib
Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism
Xiangrong Zeng | Daojian Zeng | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The relational facts in sentences are often complicated. Different relational triplets may have overlaps in a sentence. We divided the sentences into three types according to triplet overlap degree, including Normal, EntityPairOverlap and SingleEntiyOverlap. Existing methods mainly focus on Normal class and fail to extract relational triplets precisely. In this paper, we propose an end-to-end model based on sequence-to-sequence learning with copy mechanism, which can jointly extract relational facts from sentences of any of these classes. We adopt two different strategies in decoding process: employing only one united decoder or applying multiple separated decoders. We test our models in two public datasets and our model outperform the baseline method significantly.

pdf bib
Pattern-revising Enhanced Simple Question Answering over Knowledge Bases
Yanchao Hao | Hao Liu | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the 27th International Conference on Computational Linguistics

Question Answering over Knowledge Bases (KB-QA), which automatically answer natural language questions based on the facts contained by a knowledge base, is one of the most important natural language processing (NLP) tasks. Simple questions constitute a large part of questions queried on the web, still being a challenge to QA systems. In this work, we propose to conduct pattern extraction and entity linking first, and put forward pattern revising procedure to mitigate the error propagation problem. In order to learn to rank candidate subject-predicate pairs to enable the relevant facts retrieval given a question, we propose to do joint fact selection enhanced by relation detection. Multi-level encodings and multi-dimension information are leveraged to strengthen the whole procedure. The experimental results demonstrate that our approach sets a new record in this task, outperforming the current state-of-the-art by an absolute large margin.

2017

pdf bib
IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations
Shangmin Guo | Kang Liu | Shizhu He | Cao Liu | Jun Zhao | Zhuoyu Wei
Proceedings of the IJCNLP 2017, Shared Tasks

The IJCNLP-2017 Multi-choice Question Answering(MCQA) task aims at exploring the performance of current Question Answering(QA) techniques via the realworld complex questions collected from Chinese Senior High School Entrance Examination papers and CK12 website1. The questions are all 4-way multi-choice questions writing in Chinese and English respectively that cover a wide range of subjects, e.g. Biology, History, Life Science and etc. And, all questions are restrained within the elementary and middle school level. During the whole procedure of this task, 7 teams submitted 323 runs in total. This paper describes the collected data, the format and size of these questions, formal run statistics and results, overview and performance statistics of different methods

pdf bib
Which is the Effective Way for Gaokao: Information Retrieval or Neural Networks?
Shangmin Guo | Xiangrong Zeng | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

As one of the most important test of China, Gaokao is designed to be difficult enough to distinguish the excellent high school students. In this work, we detailed the Gaokao History Multiple Choice Questions(GKHMC) and proposed two different approaches to address them using various resources. One approach is based on entity search technique (IR approach), the other is based on text entailment approach where we specifically employ deep neural networks(NN approach). The result of experiment on our collected real Gaokao questions showed that they are good at different categories of questions, that is IR approach performs much better at entity questions(EQs) while NN approach shows its advantage on sentence questions(SQs). We achieve state-of-the-art performance and show that it’s indispensable to apply hybrid method when participating in the real-world tests.

pdf bib
Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning
Shizhu He | Cao Liu | Kang Liu | Jun Zhao
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Generating answer with natural language sentence is very important in real-world question answering systems, which needs to obtain a right answer as well as a coherent natural response. In this paper, we propose an end-to-end question answering system called COREQA in sequence-to-sequence learning, which incorporates copying and retrieving mechanisms to generate natural answers within an encoder-decoder framework. Specifically, in COREQA, the semantic units (words, phrases and entities) in a natural answer are dynamically predicted from the vocabulary, copied from the given question and/or retrieved from the corresponding knowledge base jointly. Our empirical study on both synthetic and real-world datasets demonstrates the efficiency of COREQA, which is able to generate correct, coherent and natural answers for knowledge inquired questions.

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

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

2016

pdf bib
Leveraging FrameNet to Improve Automatic Event Detection
Shulin Liu | Yubo Chen | Shizhu He | Kang Liu | Jun Zhao
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Learning to Represent Review with Tensor Decomposition for Spam Detection
Xuepeng Wang | Kang Liu | Shizhu He | Jun Zhao
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2015

pdf bib
Knowledge Graph Embedding via Dynamic Mapping Matrix
Guoliang Ji | Shizhu He | Liheng Xu | Kang Liu | Jun Zhao
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf bib
Question Answering over Linked Data Using First-order Logic
Shizhu He | Kang Liu | Yuanzhe Zhang | Liheng Xu | Jun Zhao
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
Statistical Machine Translation Improves Question Retrieval in Community Question Answering via Matrix Factorization
Guangyou Zhou | Fang Liu | Yang Liu | Shizhu He | Jun Zhao
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)