Zhuosheng Zhang

Ph.D. Candidate
Department of Computer Science and Engineering
Shanghai Jiao Tong University

Email: zhangzs@sjtu.edu.cn
Office: SEIEE Building 3-220

---

Publications      Shared Tasks      Awards     Personal

Profile

Zhuosheng Zhang is a Ph.D. student in the Department of Computer Science and Engineering at Shanghai Jiao Tong University, advised by Prof. Hai Zhao. He was an internship research fellow at NICT from 2019-2020, working with Prof. Rui Wang, Kehai Chen, Masao Utiyama, and Eiichiro Sumita. He received his M.S. degree from Shanghai Jiao Tong University in 2020, and B.S. degree from Wuhan University in 2016.

His research focuses on Question Answering and Dialogue Systems. In particular, he is interested in Machine Reading Comprehension (MRC) and Language Modeling (Survey). He has published more than 20 papers in top-tier NLP/ML/AI conferences and journals, including ACL, ICLR, AAAI, EMNLP, COLING, TPAMI, TKDE, TASLP, etc. He has won 1st place in various MRC shared tasks and leaderboards, such as SQuAD2.0, MuTual, RACE, SNLI, CCL-CMRC2017, etc. He was the recipient of the Academic Star Award of SJTU (2018), the National College Students of the Year Nomination Award (2016), and the CCF Elite Collegiate Award (2015).

News

• 2021/05: Two papers about dialogue pre-training and comprehension have been accpeted by ACL 2021.
• 2021/04: Our tutorial proposal about language modeling and reading comprehension has been accpeted by IJCAI 2021.
• 2021/01: Our Dialogue system (DGM) ranked 1st place on ShARC Leaderboard.
• 2021/01: One paper has been accepted by TKDE.
• 2020/12: One paper has been accepted by TPAMI.
• 2020/12: I am nominated by SJTU to participate in the Global Young Scientists Summit (GYSS) 2021.
• 2020/12: Three papers (Retro-Reader, MDFN, TADAM) have been accepted by AAAI 2021.
• 2020/09: One paper (LIMIT-BERT) has been accepted by EMNLP 2020, ACL Findings.
• 2020/09: Our MRC system ranked 1st place on MuTual Leaderboard.
• 2020/07: Our DUA paper appeared in the Google Scholar 2020 h5-index list, top 1.2% (4/331) in COLING 2018.
• 2019/12: Two papers (UVR-NMT, D2GPo) have been accepted by ICLR 2020.
• 2019/11: Four papers (SemBERT, SG-Net, DCMN+, ESC) have been accepted by AAAI 2020.
• 2019/07: Our MRC system ranked 1st place on SQuAD2.0 Leaderboard.
• 2019/06: One paper (subword_seg) has been accepted by TASLP.
• 2019/05: One paper (OpenIME) has been accepted by ACL 2019.
• 2018/10: I was honored as Academic Star in Shanghai Jiaotong University (10 total recipients of all postgraduate students from all majors in SJTU).
• 2018/05: Three papers (DUA, SubMRC, OneshotQA) have been accepted by COLING 2018.

Tutorial

• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
  Zhuosheng Zhang and Hai Zhao.
  The 30th International Joint Conference on Artificial Intelligence (IJCAI-21 Tutorial)

Invited Talk

• 2020/10: Talk at CCL 2020 Student Workshop (hosted by Prof. Jinsong Su). [slides]
• 2020/05: Talk at the UofA NLP seminar on MRC (hosted by Prof. Lili Mou). [slides]
• 2017/10: Talk at the CMRC 2017 workshop in CCL 2017 (hosted by Prof. Ting Liu). [slides]

Experience

• Jun. 2019 - Jul. 2020, Internship Research Fellow
  NICT, Kyoto, Japan. Advisor: Dr. Masao Utiyama and Prof. Rui Wang
• Jun. 2016 - Sep. 2016, Research Intern
  IBM CDL, Beijing, China. Advisor: Xinyu Wu

Education

• Sept. 2020 - Jun. 2023 (expected)
  Ph.D., Dept. of Computer Science and Engineering, Shanghai Jiao Tong University. Advisor: Prof. Hai Zhao
• Sept. 2016 - Mar. 2020
  M.S., Dept. of Computer Science and Engineering, Shanghai Jiao Tong University. Advisor: Prof. Hai Zhao
• Sept. 2012 - Jun. 2016
  B.S., Dept. of Computer Science and Engineering, Wuhan University. Advisor: Prof. Haojun Ai

Selected Publications

Discover the Full list | | | .
(#: equal contribution)
[Preprints]

• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
  Zhuosheng Zhang, Hai Zhao, Rui Wang.
  [PDF] [Abstract] [Bib] [Slides]
  
  AwesomeMRC

  Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burst of deep neural networks and the evolution of contextualized language models (CLMs), the research of MRC has experienced two significant breakthroughs. MRC and CLM, as a phenomenon, have a great impact on the NLP community. In this survey, we provide a comprehensive and comparative review on MRC covering overall research topics about 1) the origin and development of MRC and CLM, with a particular focus on the role of CLMs; 2) the impact of MRC and CLM to the NLP community; 3) the definition, datasets, and evaluation of MRC; 4) general MRC architecture and technical methods in the view of two-stage Encoder-Decoder solving architecture from the insights of the cognitive process of humans; 5) previous highlights, emerging topics, and our empirical analysis, among which we especially focus on what works in different periods of MRC researches. We propose a full-view categorization and new taxonomies on these topics. The primary views we have arrived at are that 1) MRC boosts the progress from language processing to understanding; 2) the rapid improvement of MRC systems greatly benefits from the development of CLMs; 3) the theme of MRC is gradually moving from shallow text matching to cognitive reasoning.

  @article{zhang2020mrc,
    title={Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond},
    author={Zhang, Zhuosheng and Zhao, Hai and Wang, Rui},
    journal={arXiv preprint arXiv:2005.06249},
    year={2020}
  }
                

• Advances in Multi-turn Dialogue Comprehension: A Survey
  Zhuosheng Zhang, Hai Zhao.
  [PDF] [Abstract] [Bib]
  

  Training machines to understand natural language and interact with humans is an elusive and essential task in the field of artificial intelligence. In recent years, a diversity of dialogue systems has been designed with the rapid development of deep learning researches, especially the recent pre-trained language models. Among these studies, the fundamental yet challenging part is dialogue comprehension whose role is to teach the machines to read and comprehend the dialogue context before responding. In this paper, we review the previous methods from the perspective of dialogue modeling. We summarize the characteristics and challenges of dialogue comprehension in contrast to plain-text reading comprehension. Then, we discuss three typical patterns of dialogue modeling that are widely-used in dialogue comprehension tasks such as response selection and conversation question-answering, as well as dialogue-related language modeling techniques to enhance PrLMs in dialogue scenarios. Finally, we highlight the technical advances in recent years and point out the lessons we can learn from the empirical analysis and the prospects towards a new frontier of researches.

  @article{zhang2021advances,
    title={Advances in Multi-turn Dialogue Comprehension: A Survey},
    author={Zhang, Zhuosheng and Zhao, Hai},
    journal={arXiv preprint arXiv:2103.03125},
    year={2021}
  }
                

[2021]

• Structural Pre-training for Dialogue Comprehension
  Zhuosheng Zhang, Hai Zhao.
  The 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021).

• Dialogue Graph Modeling for Conversational Machine Reading
  Siru Ouyang#, Zhuosheng Zhang#, Hai Zhao
  The 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021, Findings). [PDF] [Abstract] [Bib]
  

  Conversational Machine Reading (CMR) aims at answering questions in complicated interactive scenarios. Machine needs to answer questions through interactions with users based on given rule document, user scenario and dialogue history, and even initiatively asks questions for clarification if necessary. Namely, the answer to the task needs a machine in the response of either \textsl{Yes, No, Irrelevant} or to raise a follow-up question for further clarification. To effectively capture multiple objects in such a challenging task, graph modeling is supposed to be adopted, though it is surprising that this does not happen until this work proposes a dialogue graph modeling framework by incorporating two complementary graph models, i.e., explicit discourse graph and implicit discourse graph, which respectively capture explicit and implicit interactions hidden in the rule documents. The proposed model is evaluated on the ShARC benchmark and achieves new state-of-the-art by first exceeding the milestone accuracy score of 80\%.

  @inproceedings{ouyang2020dialogue,
    title={Dialogue Graph Modeling for Conversational Machine Reading},
    author={Ouyang, Siru and Zhang, Zhuosheng and Zhao, Hai},
    booktitle={Findings of the Association for Computational Linguistics: ACL 2021},
    year={2020}
  }
                

• Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge
  Zhuosheng Zhang, Junlong Li, Hai Zhao.
  IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2021. [PDF] [Abstract] [Bib]
  

  Multi-turn dialogue reading comprehension aims to teach machines to read dialogue contexts and solve tasks such as response selection and answering questions. The major challenges involve noisy history contexts and especial prerequisites of commonsense knowledge that is unseen in the given material. Existing works mainly focus on context and response matching approaches. This work thus makes the first attempt to tackle the above two challenges by extracting substantially important turns as pivot utterances and utilizing external knowledge to enhance the representation of context. We propose a pivot-oriented deep selection model (PoDS) on top of the Transformer-based language models for dialogue comprehension. In detail, our model first picks out the pivot utterances from the conversation history according to the semantic matching with the candidate response or question, if any. Besides, knowledge items related to the dialogue context are extracted from a knowledge graph as external knowledge. Then, the pivot utterances and the external knowledge are combined together with a well-designed mechanism for refining predictions. Experimental results on four dialogue comprehension benchmark tasks show that our proposed model achieves great improvements on baselines. A series of empirical comparisons are conducted to show how our selection strategies and the extra knowledge injection influence the results.

  @article{zhang2021kkt,
    title={Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge},
    author={Zhang, Zhuosheng and Li, Junlong and Zhao, Hai},
    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    year={2021},
  }
                

• SG-Net: Syntax Guided Transformer for Language Representation
  Zhuosheng Zhang, Yuwei Wu, Junru Zhou, Sufeng Duan, Hai Zhao, Rui Wang.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021. [PDF] [Abstract] [Bib]
  

  Understanding human language is one of the key themes of artificial intelligence. For language representation, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy texts and getting rid of the noises is essential to improve its performance. Traditional attentive models attend to all words without explicit constraint, which results in inaccurate concentration on some dispensable words. In this work, we propose using syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanisms for better linguistically motivated word representations. In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention. Syntax-guided network (SG-Net) is then composed of this extra SDOI-SAN and the SAN from the original Transformer encoder through a dual contextual architecture for better linguistics inspired representation. The proposed SG-Net is applied to typical Transformer encoders. Extensive experiments on popular benchmark tasks, including machine reading comprehension, natural language inference, and neural machine translation show the effectiveness of the proposed SG-Net design.

  @article{zhang2020sgnet,
    title={{SG-Net}: Syntax Guided Transformer for Language Representation},
    author={Zhang, Zhuosheng and Wu, Yuwei and Zhou, Junru and Duan, Sufeng and Zhao, Hai and Wang, Rui},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year={2020},
    doi={10.1109/TPAMI.2020.3046683},
    publisher={IEEE}
  }
                

• Text Compression-aided Transformer Encoding
  Zuchao Li, Zhuosheng Zhang, Hai Zhao, Rui Wang, Kehai Chen, Masao Utiyama, and Eiichiro Sumita.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021. [PDF] [Abstract] [Bib]
  

  Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant improvements in the performance of many NLP tasks. Though the Transformer encoder may effectively capture general information in its resulting representations, the backbone information, meaning the gist of the input text, is not specifically focused on. In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily. Our explicit text compression approaches use dedicated models to compress text, while our implicit text compression approach simply adds an additional module to the main model to handle text compression. We propose three ways of integration, namely backbone source-side fusion, target-side fusion, and both-side fusion, to integrate the backbone information into Transformer-based models for various downstream tasks. Our evaluation on benchmark datasets shows that the proposed explicit and implicit text compression approaches improve results in comparison to strong baselines. We therefore conclude, when comparing the encodings to the baseline models, text compression helps the encoders to learn better language representations.

  @article{li2021text,
    title={Text Compression-aided Transformer Encoding},
    author={Li, Zuchao and Zhang, Zhuosheng and Zhao, Hai and Wang, Rui and Chen, Kehai and Utiyama, Masao and Sumita, Eiichiro},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year={2021},
    publisher={IEEE}
  }
                

• Retrospective Reader for Machine Reading Comprehension
  Zhuosheng Zhang, Junjie Yang, Hai Zhao.
  The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021). [PDF] [Abstract] [Bib]
  Ranking 1st on the SQuAD2.0 leaderboard.
  
  Retro-Reader

  Machine reading comprehension (MRC) is an AI challenge that requires machine to determine the correct answers to questions based on a given passage. MRC systems must not only answer question when necessary but also distinguish when no answer is available according to the given passage and then tactfully abstain from answering. When unanswerable questions are involved in the MRC task, an essential verification module called verifier is especially required in addition to the encoder, though the latest practice on MRC modeling still most benefits from adopting well pre-trained language models as the encoder block by only focusing on the "reading". This paper devotes itself to exploring better verifier design for the MRC task with unanswerable questions. Inspired by how humans solve reading comprehension questions, we proposed a retrospective reader (Retro-Reader) that integrates two stages of reading and verification strategies: 1) sketchy reading that briefly investigates the overall interactions of passage and question, and yield an initial judgment; 2) intensive reading that verifies the answer and gives the final prediction. The proposed reader is evaluated on two benchmark MRC challenge datasets SQuAD2.0 and NewsQA, achieving new state-of-the-art results. Significance tests show that our model is significantly better than the strong ELECTRA and ALBERT baselines. A series of analysis is also conducted to interpret the effectiveness of the proposed reader.

  @inproceedings{zhang2021retro,
    title={Retrospective Reader for Machine Reading Comprehension},
    author={Zhang, Zhuosheng and Yang, Junjie and Zhao, Hai},
    booktitle={The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)},
    year={2021}
  }
                

• Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue
  Longxiang Liu#, Zhuosheng Zhang#, Hai Zhao, Xi Zhou, Xiang Zhou.
  The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021). [PDF] [Abstract] [Bib]
  Ranking 1st on the MuTual leaderboard.
  
  MDFN

  A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn dialogue modeling, the pre-trained language models (PrLMs) as encoder represent the dialogues coarsely by taking the pairwise dialogue history and candidate response as a whole, the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose a novel model to fill such a gap by modeling the effective utterance-aware and speaker-aware representations entailed in a dialogue history. In detail, we decouple the contextualized word representations by masking mechanisms in Transformer-based PrLM, making each word only focus on the words in current utterance, other utterances, two speaker roles (i.e., utterances of sender and utterances of receiver), respectively. Experimental results show that our method boosts the strong ELECTRA baseline substantially in four public benchmark datasets, and achieves various new state-of-the-art performance over previous methods. A series of ablation studies are conducted to demonstrate the effectiveness of our method.

  @inproceedings{liu2021filling,
    title={Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue},
    author={Liu, Longxiang and Zhang, Zhuosheng and and Zhao, Hai and Zhou, Xi and Zhou, Xiang},
    booktitle={The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)},
    year={2021}
  }
                

• Topic-Aware Multi-turn Dialogue Modeling
  Yi Xu, Hai Zhao, Zhuosheng Zhang
  The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021). [PDF] [Abstract] [Bib]
  
  TADAM

  In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances. As a conversation goes on, topic shift at discourse-level naturally happens through the continuous multi-turn dialogue context. However, all known retrieval-based systems are satisfied with exploiting local topic words for context utterance representation but fail to capture such essential global topic-aware clues at discourse-level. Instead of taking topic-agnostic n-gram utterance as processing unit for matching purpose in existing systems, this paper presents a novel topic-aware solution for multi-turn dialogue modeling, which segments and extracts topic-aware utterances in an unsupervised way, so that the resulted model is capable of capturing salient topic shift at discourse-level in need and thus effectively track topic flow during multi-turn conversation. Our topic-aware modeling is implemented by a newly proposed unsupervised topic-aware segmentation algorithm and Topic-Aware Dual-attention Matching (TADAM) Network, which matches each topic segment with the response in a dual cross-attention way. Experimental results on three public datasets show TADAM can outperform the state-of-the-art method by a large margin, especially by 3.4% on E-commerce dataset that has an obvious topic shift.

  @inproceedings{xu2021topic,
    title={Topic-aware multi-turn dialogue modeling},
    author={Xu, Yi and Zhao, Hai and Zhang, Zhuosheng},
    booktitle={The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)},
    year={2021}
  }
                

• Open Named Entity Modeling from Embedding Distribution
  Ying Luo*, Hai Zhao, Zhuosheng Zhang*, Bingjie Tang.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021. [PDF] [Abstract] [Bib]
  

  In this paper, we report our discovery on named entity distribution in general word embedding space, which helps an open definition on multilingual named entity definition rather than previous closed and constraint definition on named entities through a named entity dictionary, which is usually derived from human labor and replies on schedule update. Our initial visualization of monolingual word embeddings indicates named entities tend to gather together despite of named entity types and language difference, which enable us to model all named entities using a specific geometric structure inside embedding space, namely, the named entity hypersphere. For monolingual case, the proposed named entity model gives an open description on diverse named entity types and different languages. For cross-lingual case, mapping the proposed named entity model provides a novel way to build named entity dataset for resource-poor languages. At last, the proposed named entity model may be shown as a very useful clue to significantly enhance state-of-the-art named entity recognition systems generally.

  @article{luo2021open,
    title={Open Named Entity Modeling from Embedding Distribution},
    author={Luo, Ying and Zhao, Hai and Zhang, Zhuosheng and Tang, Bingjie},
    journal={IEEE Transactions on Knowledge and Data Engineering},
    year={2021},
    doi={10.1109/TKDE.2021.3049654},
    publisher={IEEE}
  }
                

• Multi-span Style Extraction for Generative Reading Comprehension
  Junjie Yang, Zhuosheng Zhang, Hai Zhao.
  The AAAI-21 Workshop on Scientific Document Understanding (SDU@AAAI-21). [PDF] [Abstract] [Bib]
  

  Generative machine reading comprehension (MRC) requires a model to generate well-formed answers. For this type of MRC, answer generation method is crucial to the model performance. However, generative models, which are supposed to be the right model for the task, in generally perform poorly. At the same time, single-span extraction models have been proven effective for extractive MRC, where the answer is constrained to a single span in the passage. Nevertheless, they generally suffer from generating incomplete answers or introducing redundant words when applied to the generative MRC. Thus, we extend the single-span extraction method to multi-span, proposing a new framework which enables generative MRC to be smoothly solved as multi-span extraction. Thorough experiments demonstrate that this novel approach can alleviate the dilemma between generative models and single-span models and produce answers with better-formed syntax and semantics. We will open-source our code for the research community.

  @inproceedings{Yang2021musst,
    title={Multi-span Style Extraction for Generative Reading Comprehension},
    author={Yang, Junjie and Zhang, Zhuosheng and Zhao, Hai},
    booktitle={The AAAI-21 Workshop on Scientific Document Understanding (SDU@AAAI-21)},
    year={2021}
  }
                

[2020]

• Neural Machine Translation with Universal Visual Representation
  Zhuosheng Zhang, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Zuchao Li, Hai Zhao.
  International Conference on Learning Representations (ICLR 2020). [PDF] [Abstract] [Bib] [Video]
  Spotlight Oral, acceptance rate: 4.16%.
  
  UVR-NMT

  Though visual information has been introduced for enhancing neural machine translation (NMT), its effectiveness strongly relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we present a universal visual representation learned over the monolingual corpora with image annotations, which overcomes the lack of large-scale bilingual sentence-image pairs, thereby extending image applicability in NMT. In detail, a group of images with similar topics to the source sentence will be retrieved from a light topic-image lookup table learned over the existing sentence-image pairs, and then is encoded as image representations by a pre-trained ResNet. An attention layer with a gated weighting is to fuse the visual information and text information as input to the decoder for predicting target translations. In particular, the proposed method enables the visual information to be integrated into large-scale text-only NMT in addition to the multimodel NMT. Experiments on four widely used translation datasets, including the WMT'16 English-to-Romanian, WMT'14 English-to-German, WMT'14 English-to-French, and Multi30K, show that the proposed approach achieves significant improvements over strong baselines.

  @inproceedings{zhang2020neural,
  title={Neural Machine Translation with Universal Visual Representation},
  author={Zhuosheng Zhang and Kehai Chen and Rui Wang and Masao Utiyama and Eiichiro Sumita and Zuchao Li and Hai Zhao},
  booktitle={International Conference on Learning Representations},
  year={2020},
  url={https://openreview.net/forum?id=Byl8hhNYPS}
  }
                

• Data-dependent Gaussian Prior Objective for Language Generation
  Zuchao Li, Rui Wang, Kehai Chen, Masso Utiyama, Eiichiro Sumita, Zhuosheng Zhang, Hai Zhao.
  International Conference on Learning Representations (ICLR 2020). [PDF]

• Semantics-aware BERT for Natural Language Understanding
  Zhuosheng Zhang, Yuwei Wu, Hai Zhao, Zuchao Li, Shuailiang Zhang, Xi Zhou, Xiang Zhou.
  The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020). [PDF] [Abstract] [Bib]
  Ranking 1st on the SNLI leaderboard.
  
  SemBERT

  The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks. However, the existing language representation models including ELMo, GPT and BERT only exploit plain context-sensitive features such as character or word embeddings. They rarely consider incorporating structured semantic information which can provide rich semantics for language representation. To promote natural language understanding, we propose to incorporate explicit contextual semantics from pre-trained semantic role labeling, and introduce an improved language representation model, Semantics-aware BERT (SemBERT), which is capable of explicitly absorbing contextual semantics over a BERT backbone. SemBERT keeps the convenient usability of its BERT precursor in a light fine-tuning way without substantial task-specific modifications. Compared with BERT, semantics-aware BERT is as simple in concept but more powerful. It obtains new state-of-the-art or substantially improves results on ten reading comprehension and language inference tasks.

  @inproceedings{zhang2020semantics,
    title={Semantics-aware bert for language understanding},
    author={Zhang, Zhuosheng and Wu, Yuwei and Zhao, Hai and Li, Zuchao and Zhang, Shuailiang and Zhou, Xi and Zhou, Xiang},
    booktitle={Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-2020)},
    volume={34},
    number={05},
    pages={9628--9635},
    year={2020}
  }
  
                

• Syntax-Guided Machine Reading Comprehension
  Zhuosheng Zhang, Yuwei Wu, Junru Zhou, Sufeng Duan, Hai Zhao, Rui Wang.
  The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020). [PDF] [Abstract] [Bib]
  The first single model to surpass human benchmark on the SQuAD2.0 leaderboard.
  
  SG-Net

  For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is essential to improve its performance. Traditional attentive models attend to all words without explicit constraint, which results in inaccurate concentration on some dispensable words. In this work, we propose using syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanism for better linguistically motivated word representations. In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention. Syntax-guided network (SG-Net) is then composed of this extra SDOI-SAN and the SAN from the original Transformer encoder through a dual contextual architecture for better linguistics inspired representation. To verify its effectiveness, the proposed SG-Net is applied to typical pre-trained language model BERT which is right based on a Transformer encoder. Extensive experiments on popular benchmarks including SQuAD 2.0 and RACE show that the proposed SG-Net design helps achieve substantial performance improvement over strong baselines.

  @inproceedings{zhang2020sg,
    title={SG-Net: Syntax-Guided Machine Reading Comprehension.},
    author={Zhang, Zhuosheng and Wu, Yuwei and Zhou, Junru and Duan, Sufeng and Zhao, Hai and Wang, Rui},
    booktitle={Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-2020)},
    pages={9636--9643},
    year={2020}
  }
  
                

• DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension
  Shuailiang Zhang, Hai Zhao, Yuwei Wu, Zhuosheng Zhang, Xi Zhou, Xiang Zhou.
  The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020). [PDF] [Abstract] [Bib]
  Ranking 1st on the RACE leaderboard.
  
  DCMN

@inproceedings{zhang2020dcmn+,
  title={{DCMN+}: Dual co-matching network for multi-choice reading comprehension},
  author={Zhang, Shuailiang and Zhao, Hai and Wu, Yuwei and Zhang, Zhuosheng and Zhou, Xi and Zhou, Xiang},
  booktitle={Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-2020)},
  volume={34},
  number={05},
  pages={9563--9570},
  year={2020}
}

              

• Explicit Sentence Compression for Neural Machine Translation
  Zuchao Li, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Zhuosheng Zhang, Hai Zhao.
  The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).

• LIMIT-BERT: Linguistic Informed Multi-task BERT
  Junru Zhou, Zhuosheng Zhang, Hai Zhao, Shuailiang Zhang.
  The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020). ACL Findings. [PDF] [Abstract] [Bib]
  
  LIMIT-BERT

  In this paper, we present a Linguistic Informed Multi-Task BERT (LIMIT-BERT) for learning language representations across multiple linguistic tasks by Multi-Task Learning (MTL). LIMIT-BERT includes five key linguistic syntax and semantics tasks: Part-Of-Speech (POS) tags, constituent and dependency syntactic parsing, span and dependency semantic role labeling (SRL). Besides, LIMIT-BERT adopts linguistics mask strategy: Syntactic and Semantic Phrase Masking which mask all of the tokens corresponding to a syntactic/semantic phrase. Different from recent Multi-Task Deep Neural Networks (MT-DNN) (Liu et al., 2019), our LIMIT-BERT is linguistically motivated and learning in a semi-supervised method which provides large amounts of linguistic-task data as same as BERT learning corpus. As a result, LIMIT-BERT not only improves linguistic tasks performance but also benefits from a regularization effect and linguistic information that leads to more general representations to help adapt to new tasks and domains. LIMIT-BERT obtains new state-of-the-art or competitive results on both span and dependency semantic parsing on Propbank benchmarks and both dependency and constituent syntactic parsing on Penn Treebank.

  @inproceedings{zhou2020limit,
    title={LIMIT-BERT: Linguistic informed multi-task bert},
    author={Zhou, Junru and Zhang, Zhuosheng and Zhao, Hai and Zhang, Shuailiang},
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.findings-emnlp.399",
    doi = "10.18653/v1/2020.findings-emnlp.399",
    pages = "4450--4461",
  }
                

• Memory Network for Linguistic Structure Parsing
  Zuchao Li, Chaoyu Guan, Hai Zhao, Rui Wang, Kevin Parnow, Zhuosheng Zhang.
  IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2020, 28: 2743-2755. [PDF] [Abstract] [Bib]
  

  Memory-based learning can be characterized as a lazy learning method in machine learning terminology because it delays the processing of input by storing the input until needed. Linguistic structure parsing, which has been in a performance improvement bottleneck since the latest series of works was presented, determines the syntactic or semantic structure of a sentence. In this article, we construct a memory component and use it to augment a linguistic structure parser which allows the parser to directly extract patterns from the known training treebank to form memory. The experimental results show that existing state-of-the-art parsers reach new heights of performance on the main benchmarks for dependency parsing and semantic role labeling with this memory network.

  @article{li2020memory,
    title={Memory Network for Linguistic Structure Parsing},
    author={Li, Zuchao and Guan, Chaoyu and Zhao, Hai and Wang, Rui and Parnow, Kevin and Zhang, Zhuosheng},
    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    volume={28},
    pages={2743--2755},
    year={2020},
    publisher={IEEE}
  }
  
                

• Open Vocabulary Learning for Neural Chinese Pinyin IME
  Zhuosheng Zhang, Yafang Huang, Hai Zhao.
  The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019). [PDF] [Abstract] [Bib]
  
  OpenIME

  Pinyin-to-character (P2C) conversion is the core component of pinyin-based Chinese input method engine (IME). However, the conversion is seriously compromised by the ambiguities of Chinese characters corresponding to pinyin as well as the predefined fixed vocabularies. To alleviate such inconveniences, we propose a neural P2C conversion model augmented by a large online updating vocabulary with a target vocabulary sampling mechanism to support an open vocabulary learning during IME working. Our experiments show that the proposed approach reduces the decoding time on CPUs up to 50$\%$ on P2C tasks at the same or only negligible change in conversion accuracy, and the online updated vocabulary indeed helps our IME effectively follows user inputting behavior.

  @inproceedings{zhang2019acl,
  	title = "Open Vocabulary Learning for Neural {Chinese} Pinyin {IME}",
  	author = "Zhang, Zhuosheng and Huang, Yafang and Zhao, Hai",
  	booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)",
  	url = "https://www.aclweb.org/anthology/P19-1154",
  	pages = "1584--1594",
  	year = "2019",
  }
                

• Effective Subword Segmentation for Text Comprehension
  Zhuosheng Zhang, Hai Zhao, Kangwei Ling, Jiangtong Li, Zuchao Li, Shexia He, Guohong Fu.
  IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2019, 27(11): 1664-1674. [PDF] [Abstract] [Bib]
  
  subword_seg

  Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or complex words. However, character itself is not a natural minimal linguistic unit for representation or word embedding composing due to ignoring the linguistic coherence of consecutive characters inside word. This paper presents a general subword-augmented embedding framework for learning and composing computationally-derived subword-level representations. We survey a series of unsupervised segmentation methods for subword acquisition and different subword-augmented strategies for text understanding, showing that subword-augmented embedding significantly improves our baselines in various types of text understanding tasks on both English and Chinese benchmarks.

  @article{Zhang2019subword,
  	title={Effective Subword Segmentation for Text Comprehension},
  	author={Zhang, Zhuosheng and Zhao, Hai and Ling, Kangwei and Li, Jiangtong and He, Shexia and Fu, Guohong},
  	journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)},
  	year={2019},
  	volume={27},
  	number={11},
  	pages={1664-1674},
  	doi={10.1109/TASLP.2019.2922537}
  }
                

• Explicit Contextual Semantics for Text Comprehension
  Zhuosheng Zhang, Yuwei Wu, Zuchao Li and Hai Zhao.
  The 33rd Pacific Asia Conference on Language, Information and Computation (PACLIC 33). [PDF] [Abstract] [Bib]

  Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL) task. Despite of sharing a lot of processing characteristics and even task purpose, it is surprisingly that jointly considering these two related tasks was never formally reported in previous work. Thus this paper makes the first attempt to let SRL enhance text comprehension and inference through specifying verbal predicates and their corresponding semantic roles. In terms of deep learning models, our embeddings are enhanced by explicit contextual semantic role labels for more fine-grained semantics. We show that the salient labels can be conveniently added to existing models and significantly improve deep learning models in challenging text comprehension tasks. Extensive experiments on benchmark machine reading comprehension and inference datasets verify that the proposed semantic learning helps our system reach new state-of-the-art over strong baselines which have been enhanced by well pretrained language models from the latest progress.

  @inproceedings{zhang2019explicit,
  	title = "Explicit Contextual Semantics for Text Comprehension",
  	author = "Zhang, Zhuosheng and Wu, Yuwei and Li, Zuchao and Zhao, Hai",
  	booktitle = "Proceedings of the 33rd Pacific Asia Conference on Language, Information and Computation (PACLIC 33)",
  	year = "2019",
  }
                

• SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing
  Zuchao Li, Hai Zhao, Zhuosheng Zhang, Rui Wang, Masao Utiyama, and Eiichiro Sumita.
  2019 Conference on Computational Natural Language Learning (CoNLL 2019). [PDF]

• Examination-Style Reading Comprehension with Neural augmented Retrieval
  Yiqing Zhang, Hai Zhao, Zhuosheng Zhang.
  International Conference on Asian Language Processing (IALP 2019).

• Dependency or Span, End-to-End Uniform Semantic Role Labeling
  Zuchao Li, Shexia He, Hai Zhao, Yiqing Zhang, Zhuosheng Zhang, Xi Zhou, Xiang Zhou.
  The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019). [Abstract] [Bib] [Source]

  Semantic role labeling (SRL) aims to discover the predicate-argument structure of a sentence. End-to-end SRL withoutsyntactic input has received great attention. However, mostof them focus on either span-based or dependency-based semantic representation form and only show specific model optimization respectively. Meanwhile, handling these two SRL tasks uniformly was less successful. This paper presents an end-to-end model for both dependency and span SRL with a unified argument representation to deal with two different types of argument annotations in a uniform fashion. Furthermore, we jointly predict all predicates and arguments,especially including long-term ignored predicate identification subtask. Our single model achieves new state-of-the-artresults on both span (CoNLL 2005, 2012) and dependency(CoNLL 2008, 2009) SRL benchmarks.

• Modeling Multi-turn Conversation with Deep Utterance Aggregation
  Zhuosheng Zhang, Jiangtong Li, Pengfei Zhu, Hai Zhao and Gongshen Liu.
  The 27th International Conference on Computational Linguistics (COLING 2018). [PDF] [Abstract] [Bib]
  Appeared in the Google Scholar 2020 h5-index list, top 1.2% (4/331) in COLING 2018.
  DeepUtteranceAggregation

  Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the model matches a response with each refined utterance and the final matching score is obtained after attentive turns aggregation. Experimental results show our model outperforms the state-of-the-art methods on three multi-turn conversation benchmarks, including a newly introduced e-commerce dialogue corpus.

  @inproceedings{zhang2018dua,
                  title = {Modeling Multi-turn Conversation with Deep Utterance Aggregation},
                  author = {Zhang, Zhuosheng and Li, Jiangtong and Zhu, Pengfei and Zhao, Hai},
                  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018)},
                  pages= {3740–-3752},
                  year = {2018},
              }
                

• Subword-augmented Embedding for Cloze Reading Comprehension
  Zhuosheng Zhang, Yafang Huang and Hai Zhao.
  The 27th International Conference on Computational Linguistics (COLING 2018). [PDF] [Abstract] [Bib]
  Ranking 1st on the CCL-CMRC 2017 shared task (single model).
  
  subMrc

  Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the minimal linguistic unit. In addition, with a simple concatenation of character and word embedding, previous models actually give suboptimal solution. In this paper, we propose to use subword rather than character for word embedding enhancement. We also empirically explore different augmentation strategies on subword-augmented embedding to enhance the cloze-style reading comprehension model reader. In detail, we present a reader that uses subword-level representation to augment word embedding with a short list to handle rare words effectively. A thorough examination is conducted to evaluate the comprehensive performance and generalization ability of the proposed reader. Experimental results show that the proposed approach helps the reader significantly outperform the state-of-the-art baselines on various public datasets.

  @inproceedings{zhang2018mrc,
                  title = {Subword-augmented Embedding for Cloze Reading Comprehension},
                  author = {Zhang, Zhuosheng and Huang,Yafang and Zhao, Hai},
                  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018)},
                  pages = {1802-–1814},
                  year = {2018},
              }
                

• One-shot Learning for Question-Answering in Gaokao History Challenge
  Zhuosheng Zhang and Hai Zhao.
  The 27th International Conference on Computational Linguistics (COLING 2018). [PDF] [Abstract] [Bib]
  
  OneshotQA

  Answering questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between questions and answers. In this work, we propose a hybrid neural model for deep question-answering task from history examinations. Our model employs a cooperative gated neural network to retrieve answers with the assistance of extra labels given by a neural turing machine labeler. Empirical study shows that the labeler works well with only a small training dataset and the gated mechanism is good at fetching the semantic representation of lengthy answers. Experiments on question answering demonstrate the proposed model obtains substantial performance gains over various neural model baselines in terms of multiple evaluation metrics.

  @inproceedings{zhang2018gaokao,
                  title = {One-shot Learning for Question-Answering in Gaokao History Challenge},
                  author = {Zhang, Zhuosheng and Zhao, Hai},
                  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018)},
                  pages = {449–-461},
                  year = {2018},
              }
                

• Effective Character-augmented Word Embedding for Machine Reading Comprehension
  Zhuosheng Zhang, Yafang Huang, Pengfei Zhu, Hai Zhao.
  The Seventh CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2018). [PDF] [Abstract] [Bib]

  Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate word and character level representations, which has been shown suboptimal for the concerned task. In this paper, we empirically explore different integration strategies of word and character embeddings and propose a character-augmented reader which attends character-level representation to augment word embedding with a short list to improve word representations, especially for rare words. Experimental results show that the proposed approach helps the baseline model significantly outperform state-of-the-art baselines on various public benchmarks.

  @inproceedings{zhang2018char,
                  title = {Effective Character-augmented Word Embedding for Machine Reading Comprehension},
                  author = {Zhang, Zhuosheng and Huang, Yafang and Zhu, Pengfei and Zhao, Hai},
                  booktitle = {Proceedings of the Seventh CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2018)},
                  pages = {27-39},
                  year = {2018},
              }
                

• Neural Hypernym Discovery with Term Embeddings
  Zhuosheng Zhang, Jiangtong Li, Hai Zhao, Bingjie Tang.
  International Workshop on Semantic Evaluation (SemEval 2018), workshop of NAACL-HLT 2018. [PDF] [Abstract] [Bib]

  This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts or entities, given the search space of a pre-defined vocabulary. We introduce a neural network architecture for the concerned task and empirically study various neural network models to build the representations in latent space for words and phrases. The evaluated models include convolutional neural network, long-short term memory network, gated recurrent unit and recurrent convolutional neural network. We also explore different embedding methods, including word embedding and sense embedding for better performance.

  @InProceedings{Zhang2018Neural,
                  title={{SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings}},
                  author={Zhang, Zhuosheng and Li, Jiangtong and Zhao, Hai and Tang, Bingjie},
                  booktitle={Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018)},
                  year={2018}, 
                  pages = {903–908},
                  address={New Orleans, LA, United States},
                  publisher = {Association for Computational Linguistics}
              }
  		  

• Lingke: A Fine-grained Multi-turn Chatbot for Customer Service
  Pengfei Zhu, Zhuosheng Zhang, Jiangtong Li, Yafang Huang, Hai Zhao.
  The 27th International Conference on Computational Linguistics (COLING 2018), Demo Track. [PDF] [Abstract] [Bib] [Demo]

  Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations.

  @inproceedings{zhu2018lingke,
                  title = {Lingke: A Fine-grained Multi-turn Chatbot for Customer Service},
                  author = {Zhu, Pengfei and Zhang, Zhuosheng and Li, Jiangtong and Huang, Yafang and Zhao, Hai},
                  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018), System Demonstrations},
                  pages = {108-–112},
                  year = {2018},
              }
                

• Neural-based Chinese Pinyin Aided Input Method with Customizable Association
  Yafang Huang*, Zuchao Li*, Zhuosheng Zhang, Hai Zhao.
  The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Demo Track. [PDF] [Abstract] [Bib] [Demo]

  Chinese pinyin input method engine(IME) lets user conveniently input Chinese into a computer by typing pinyin through the common keyboard. In addition to offering high conversion quality, modern pinyin IME is supposed to aid user input with extended association function. However, existing solutions for such functions are roughly based on oversimplified matching algorithms at word-level, whose resulting products provide limited extension associated with user inputs. This work presents the Moon IME, a pinyin IME that integrates the attention-based neural machine translation (NMT) model and Information Retrieval (IR) to offer amusive and customizable association ability. The released IME is implemented on Windows via text services framework.

  @inproceedings{Huang2018Moon,
                      title={{Moon IME:} Neural-based Chinese Pinyin Aided Input Method with Customizable Association},
                      author={Huang,Yafang and Li,Zuchao and Zhang,Zhuosheng and Zhao,Hai},
                      booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), System Demonstrations},
                      pages = {140–145},
                      year={2018}
                  }
                

• A Unified Syntax-aware Framework for Semantic Role Labeling
  Zuchao Li, Shexia He, Jiaxun Cai, Zhuosheng Zhang, Hai Zhao, Gongshen Liu, Linlin Li, Luo Si.
  2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018). [PDF] [Abstract] [Bib]

  Semantic role labeling (SRL) aims to recognize the predicate-argument structure of a sentence. Syntactic information has been paid a great attention over the role of enhancing SRL. However, the latest advance shows that syntax would not be so important for SRL with the emerging much smaller gap be-tween syntax-aware and syntax-agnostic SRL. To comprehensively explore the role of syntax for SRL task, we extend existing models and propose a unified framework to investigate more effective and more diverse ways of incorporating syntax into sequential neural networks. Exploring the effect of syntactic input quality on SRL performance, we confirm that high-quality syntactic parse could still effectively enhance syntactically-driven SRL. Using empirically optimized integration strategy, we even enlarge the gap between syntax-aware and syntax-agnostic SRL. Ourframework achieves state-of-the-art results on CoNLL-2009 benchmarks both for English and Chinese, substantially outperforming all previous models.

  @inproceedings{li2018unified,
  	title={A unified syntax-aware framework for semantic role labeling},
  	author={Li, Zuchao and He, Shexia and Cai, Jiaxun and Zhang, Zhuosheng and Zhao, Hai and Liu, Gongshen and Li, Linlin and Si, Luo},
  	booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)},
  	pages={2401--2411},
  	year={2018}
  }
                

• Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing
  Zuchao Li, Shexia He, Zhuosheng Zhang and Hai Zhao.
  2018 Conference on Computational Natural Language Learning (CoNLL 2018). [PDF] [Abstract] [Bib]

  This paper describes the system of team LeisureX in the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system predicts the POS tag and dependency tree jointly. For the basic tasks, including tokenization, lemmatization and morphology prediction, we employ the official baseline model (UDPipe). To train the lowresource languages, we adopt a sampling method based on other rich-resource languages. Our system achieves a macroaverage of 68.31% LAS F1 score despite of single model, with an improvement of 2.51% compared with the UDPipe.

  @inproceedings{Li2018joint,
                  title = {Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing},
                  author = {Zuchao Li, Shexia He, Zhuosheng Zhang and Hai Zhao },
                  booktitle = {CoNLL 2018: The SIGNLL Conference on Computational Natural Language Learning},
                  year = {2018},
              }
                

• Intelligent Library System Using iBeacon Firmwares
  Zhuosheng Zhang, Haojun Ai, Jingyuan Xue, Fangfang Ma, Shengyuan Zhangyin.
  Electronic Engineering & Product World for Engineering Managers & Desingers, 2015, (1): 16-21. [PDF] [Abstract] [Bib]

  According to technical architecture of internet of things, we designed a comprehensive solution for the intelligent library system based on the iBeacon indoor positioning technology, 3D-based real-scene, mobile Internet, and SaaS model, etc. This solution supported multiple services, such as the intelligent positioning and navigation service, reality-augmented location aware service , 3D space supervision, personalized service. For the readers, they can acquire diversiform service, such as intelligent book retrieval, library navigation, message push. For the librarians, they can obtain the details of readers and the operation condition of the library by the use of Unity3D to build the scene of the library. The indoor location solution was designed based on the RF fingerprint of iBeacons, in which the KNN, the Inverse Distance to a Power and the IMU sensors were used. The precision of this algorithm is better than the trilateration. As for system deployment and maintainability, our system is be superior to the positioning system based on WI-FI. The opened API was provided to the third party application in the service layer of the SaaS architecture where KVP standard is used in the HTTP access requirement. J2EE framework was used to provide the appropriate interface for the internet of things architecture. Multiple devices, library space information and user registration can be managed in the perception layer, data layer and application layer.

  		  @article{张倬胜2015,
  			  title={基于iBeacon定位技术的智慧图书馆},
  			  author={张倬胜 and 艾浩军 and 马方方 and 薛静远 and 章尹圣原 and 艾浩军},
  			  journal={电子产品世界},
  			  number={1},
  			  pages={31-35},
  			  year={2015},
  			}
  		  

• Research on elaborate indoor positioning method based on iBeacon Firmwares
  Zhuosheng Zhang, Haojun Ai, Fangfang Ma, Jingyuan Xue, Shengyuan Zhangyin.
  Geomatics World, 2015, (2): 26-30. [PDF] [Abstract] [Bib]

  Apple released iBeacon as a rough-precision position sensing distance service system, which has attracted extensive attention. For more sophisticated wide-area location services, wireless fingerprinting positioning method is proposed based on iBeacon, and we give an example of location based service system of library.

  		  @article{张倬胜2015,
  			  title={基于iBeacon的精细室内定位方法研究},
  			  author={张倬胜 and 马方方 and 薛静远 and 艾浩军},
  			  journal={地理信息世界},
  			  number={02},
  			  pages={26-30},
  			  year={2015},
  			}
  		  

Shared Tasks

• The best among all submissions.
[Leaderboard] [Paper]

• The best among all submissions.
[Leaderboard] [Paper]

• The best models for both single and ensemble settings among all submissions (2020.01).
• The first to surpass human benchmark on both EM and F1 scores with a single model (from 2019.07-09).
• The first time to exceed 90% F1 score with ensemble models.
  [Leaderboard] [Paper] [Report]

• The best among all submissions.
• The best among all academic submissions.
  [Leaderboard] [Paper] [Report]

• The best among all submissions.
  [Leaderboard] [Paper]

• The 3rd best among all submissions.
• The best among all academic submissions.
  [Leaderboard] [Paper]

• The best single system and the second ensemble system (Silver Medal).
  [Leaderboard] [Paper] [Source]

Professional Service

• Program Committee Member:
  • CL/NLP conferences: ACL (2020, 2021), EMNLP (2021), COLING (2020), AACL (2020), NAACL (2021), ACL Rolling Review
  • ML/AI conferences: ICLR (2021), NeurIPS (2021), AAAI (2020, 2021)

• Journal Reviewer: ACM Trans. on ALLIP (TALLIP), Neurocomputing.

• Teaching Assistant for "Natural language understanding", Shanghai Jiao Tong University, Spring 2018, Spring 2019, and Spring 2021.

Honorships

• National Scholarship for Graduate Student (2018 & 2020), Ministry of Education of P.R.China

• Excellent M.S. Student Scholarship of Yang Yuanqing Education Fund, Shanghai Jiao Tong University

• Academic Star of Graduate Students (上海交通大学研究生学术之星), Shanghai Jiao Tong University

• National Annual Figures Nomination of College Students (中国大学生年度人物提名奖), Ministry of Education of P.R.China

• The CCF Elite Collegiate Award (CCF优秀大学生), China Computer Federation

• First Prize at 2018 IBM Watson Build Chatbot Competition, IBM China

• First Prize at 2018 Jiaxing E-commerce Innovation Competition, Jiaxing municipal Bureau of Commerce

• First Prize at 2017 IBM Hackathon, IBM China

• Outstanding Bachelor Thesis Award, Hubei Provincial Department of Education

• First Prize in the 2014&2015 TI Cup National Internet of Things Competition, CS Committee in Ministry of Education of P.R.China

Hobbies

• Traveling
• Playing video games
• Listening to music, playing instruments (esp. ErHu , level-6)

Miscellaneous

• Now, a few words on looking for things. When you go looking for something specific, your chances of finding it are very bad. Because of all the things in the world, you're only looking for one of them. When you go looking for anything at all, your chances of finding it are very good. Because of all the things in the world, you're sure to find some of them.
  -- The Zero Effect

• Never give up the faith, pass on the torch, and keep the light burning.
  念念不忘，必有回响。
  -- The Grandmaster《一代宗师》