陈科海 (Chen, Kehai)

I have been an assistant professor in School of Computer Science and Technology at Harbin Institute of Technolgy, Shenzhen, China since Jan, 2022. My research interesting focuses on Machine Translation, and Natural Language Processing. I have published more than 30 papers top-tier NLP/ML/AI conferences and journals, such as ACL, EMNLP, ICLR, AAAI, TPAMI, TASLP, TFS, etc. I served as the Senior Program Committee of AAAI-2021/2022 and the Area Chair of ACL-2022 and AACL-IJCNLP-2022. I gave a cutting-edge tutorial at EMNLP-2021.

E-mail: chenkehai AT hit.edu.cn; chenkehai AT gmail.com [中文主页]

Looking for self-motivated Ph.D. students (2024), Master students (2024), and Undergraduate students who want to engage in machine translation and NLP research. Please send your CV to me by email if you want to join us.

Experience

Assistant professor in School of Computer Science and Technology at Harbin Institute of Technolgy (Shenzhen), China, and join in Prof. Min Zhang's team, 2022.01~now.
Researcher in Advanced Translation Technology Laboratory (ATT-ASTREC), National Institute of Information and Communications Technology (NICT), Kyoto, Japan, 2018.11-2021.12
Ph.D in School of Computer Science of Technology, Harbin Institute of Technology (HIT), supervised by Prof. Tiejun Zhao, Harbin, China, 2013.09-2018.10
--Internship Research Fellow, NICT, co-supervised with Masao Utiyama, Rui Wang, Lemao Liu, Akihiro Tamura, and Eiichiro Sumita, 2017.01~2018.01
--He is a recipient of CIPSC (Chinese Information Processing Society of China) Best Ph.D. Thesis Awards in 2020.
Master in Computer Science, University of Chinese Academy of Sciences (UCAS), Beijing, China, 2010.09-2013.07
Bachelor in Computer Science, Xi'an University of Technology (XAUT), Xi'an, China, 2006.09-2010.07

@HIT

Ph.D. Students:
   Hongbin Zhang (2023.9~, Co-supervised with Prof. Min Zhang)
Master Student:
   Zhenyu Li (2023.9~)
   Zelin Li (2022.9~)
   Zhengsheng Guo (2022.9~, Co-supervised with Prof. Min Zhang)
   Meizhi Zhong (2022.9~, Co-supervised with Prof. Min Zhang)

Fundings

2023-2026: PI of NSFC General Program: "Research on Incomplete Contextual Information Based Simultaneous Machine Translation Modeling"
2022-2025: PI of Shenzhen College Stability Support Plan: "Research on Key Technologies of Simultaneous Machine Translation"
2021-2022: PI of Japan national funding (JSPS) for Grant-in-Aid for Research Activity Start-up: "Linguistic Typology Aware Neural Machine Translation"

Selected Publications [Google Scholar][Semantic Scholar][DBLP]

2023
  Improving Translation Quality Estimation with Bias Mitigation [Paper and Bib]
     Hui Huang, Shuangzhi Wu, Kehai Chen, Hui Di, Muyun Yang and Tiejun Zhao
     The 61th Annual Meeting of the Association for Computational Linguistics (ACL), Toronto, Canada, July, 2023
  Universal Multimodal Representation for Language Understanding [Paper and Bib]
     Zhuosheng Zhang, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Zuchao Li, and Hai Zhao
     IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2023

2022
  Document-Level Relation Extraction with Path Reasoning [Paper and Bib]
     Wang Xu, Kehai Chen, and Tiejun Zhao
     Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Accepted, November 2022
  Effective Graph Context Representation for Document-level Machine Translation [Paper and Bib]
     Kehai Chen, Muyun Yang, Masao Utiyama, Eiichiro Sumita, Rui Wang, and Min Zhang
     The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI), July, 2022
  Document-Level Relation Extraction with Sentences Importance Estimation and Focusing [Paper and Bib]
     Wang Xu, Kehai Chen, Lili Mou, and Tiejun Zhao
     The 2022 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), July, 2022
  Data-driven Fuzzy Target Representation for Intelligent Translation System [Paper and Bib]
     Kehai Chen, Muyun Yang, Tiejun Zhao, and Min Zhang
     IEEE Transactions on Fuzzy Systems (TFS), April 2022 (Early Access)
  Synchronous Refinement for Neural Machine Translation [Paper and Bib]
     Kehai Chen, Masao Utiyama, Eiichiro Sumita, Rui Wang, and Min Zhang
     The 60th Annual Meeting of the Association for Computational Linguistics (ACL-Findings), May, 2022
  Integrating Prior Translation Knowledge into Neural Machine Translation [Paper and Bib]
     Kehai Chen, Rui Wang, Masao Utiyama, and Eiichiro Sumita
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 30, pp. 330-339, 2022
  Advancing Chinese Event Detection via Revisiting Character Information [Paper and Bib]
     Yanxia Qin, Zhongqin Wang, Yue Zhang, Kehai Chen, and Min Zhang
     ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), vol. 21, No. 78, pp. 1–9, July 2022

2021
  Discriminative Reasoning for Document-level Relation Extraction [Paper and Bib]
     Wang Xu, Kehai Chen, and Tiejun Zhao
     Findings of The 59th Annual Meeting of the Association for Computational Linguistics (ACL-Findings), August, 2021
  Context-Aware Positional Representation for Self-Attention Networks [Paper and Bib]
     Kehai Chen, Rui Wang, Masao Utiyama, and Eiichiro Sumita
     Neurocomputing, Volume 451, Pages 46-563, September 2021
  Document-Level Relation Extraction with Reconstruction [Paper and Bib]
     Wang Xu, Kehai Chen, and Tiejun Zhao
     Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), February, 2021
  A Pattern Driven Graph Ranking Approach to Attribute Extraction for Knowledge Graph [Paper and Bib]
     Muyun Yang, Kehai Chen, Shuqi Sun, Zhongyuan Han, Leilei Kong, and Qingye Meng
     IEEE Transactions on Industrial Informatics, vol. 18, no. 2, pp. 1250-1259, Feb. 2021
  Modeling Future Cost for Neural Machine Translation [Paper and Bib]
     Chaoqun Duan, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Conghui Zhu, and Tiejun Zhao
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 29, pp. 770-781, 2021
  Syntax in End-to-End Natural Language Processing [Paper and Bib]
     Hai Zhao, Rui Wang, and Kehai Chen
     The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP-Tutorial), November, 2021
  Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios [Paper and Bib]
     Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita and Tiejun Zhao
     The 2021 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT), June 2021
  Text Compression-aided Transformer Encoding [Paper and Bib]
     Zuchao Li, Zhuosheng Zhang, Hai Zhao, Rui Wang, Kehai Chen, Masao Utiyama, and Eiichiro Sumita
     IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Accepted, 2021
  Unsupervised Neural Machine Translation for Similar and Distant Language Pairs: An Empirical Study [Paper and Bib]
     Haipeng Sun, Rui Wang, Masao Utiyama, Benjamin Marie, Kehai Chen, Eiichiro Sumita, and Tiejun Zhao
     ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), vol.20, April 2021

2020
  Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training [Paper and Bib]
     Haipeng Sun, Rui Wang, Kehai Chen, Xugang Lu, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao
     The 28th International Conference on Computational Linguistics (COLING), Barcelona, Spain, December, 2020
  Robust Machine Reading Comprehension by Learning Soft labels [Paper and Bib]
     Zhenyu Zhao, Shuangzhi Wu, Muyun Yang, Kehai Chen, Tiejun Zhao
     The 28th International Conference on Computational Linguistics (COLING), Barcelona, Spain, December, 2020
  Towards More Diverse Input Representation for Neural Machine Translation [Paper and Bib]
     Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao, Muyun Yang, and Hai Zhao
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 28, pp. 1586-1597, December 2020
  Content Word Aware Neural Machine Translation [Paper and Bib][Slides]
     Kehai Chen, Rui Wang, Masao Utiyama, and Eiichiro Sumita
     The 58th Annual Meeting of the Association for Computational Linguistics (ACL), Seattle, USA, July 2020
  Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation [Paper and Bib]
     Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao
     The 58th Annual Meeting of the Association for Computational Linguistics (ACL), Seattle, USA, July 2020
  End-to-end Speech Translation with Adversarial Training[Paper and Bib]
     Xuancai Li, Kehai Chen, Tiejun Zhao, and Muyun Yang
     The First Workshop on Automatic Simultaneous Translation, Seattle, USA, July 2020
  Data-dependent Gaussian Prior Objective for Language Generation [Paper and Bib]
     Zuchao Li, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Zhuosheng Zhang, and Hai Zhao
     Eighth International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, April 2020
  Neural Machine Translation with Universal Visual Representation [Paper and Bib]
     Zhuosheng Zhang, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Zuchao Li, and Hai Zhao
     Eighth International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, April 2020
  Explicit Sentence Compression for Neural Machine Translation [Paper and Bib]
     Zuchao Li, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Zhuosheng Zhang, and Hai Zhao
     Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New York, USA, February 2020
  A Novel Sentence-Level Agreement Architecture for Neural Machine Translation [Paper and Bib]
     Mingming Yang, Rui Wang, Kehai Chen, Xing Wang, Tiejun Zhao, and Min Zhang
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 28, pp. 2585-2597, 2020
  Unsupervised Neural Machine Translation with Cross-lingual Language Representation Agreement [Paper and Bib]
     Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 28, pp. 1170-1182, December 2020
  A Hierarchical Clustering Approach to Fuzzy Semantic Representation of Rare Words in Neural Machine Translation [Paper and Bib]
     Muyun Yang, Shujie Liu, Kehai Chen, Hongyang Zhang, Enbo Zhao, and Tiejun Zhao
     IEEE Transactions on Fuzzy Systems (TFS), vol. 28, no. 5, pp. 992-1002, May 2020
  Neural Machine Translation with Target-Attention Model [Paper and Bib]
     Mingming Yang, Min Zhang, Kehai Chen, Rui Wang, and Tiejun Zhao
     IEICE Transactions on Information and Systems, Vol.E103-D, No.03, pp.684-694, 2020

2019
  NICT’s Machine Translation Systems for CCMT-2019 Translation Task [Paper and Bib][Poster]
     Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita
     China Conference on Machine Translation (CCMT), Nanchang, China, Semtember 2019
  Recurrent Positional Embedding for Neural Machine Translation [Paper and Bib][Poster]
     Kehai Chen, Rui Wang, Masao Utiyama, and Eiichiro Sumita
     The 2019 Conference on Empirical Methods in Natural Language Processing and The 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, November 2019
  NICT's Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task [Paper and Bib]
     Benjamin Marie, Haipeng Sun, Rui Wang, Kehai Chen, Atsushi Fujita, Masao Utiyama and Eiichiro Sumita
     The 4th Conference on Machine Translation (WMT), Florence, Italy, July 2019
     Note: 1st in the only unsupervised MT task (German-Czech) by BLEU and human evaluation
  Neural Machine Translation with Reordering Embeddings [Paper and Bib][Slides]
     Kehai Chen, Rui Wang, Masao Utiyama, and Eiichiro Sumita
     The 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy, July 2019
  Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation [Paper and Bib]
     Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao
     The 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy, July 2019
  Sentence-Level Agreement for Neural Machine Translation [Paper and Bib]
     Mingming Yang, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Min Zhang, and Tiejun Zhao
     The 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy, July 2019
  Lattice-Based Transformer Encoder for Neural Machine Translation [Paper and Bib]
     Fengshun Xiao, Jiangtong Li, Hai Zhao, Rui Wang, and Kehai Chen
     The 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy, July 2019
  Neural Machine Translation with Sentence-level Topic Context [Paper and Bib]
     Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 27, no. 12, pp. 1970-1984, December 2019
  A Bilingual Adversarial Autoencoder for Unsupervised Bilingual Lexicon Induction [Paper and Bib]
     Xuefeng Bai, Hailong Cao, Kehai Chen, and Tiejun Zhao
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 27, no. 10, pp. 1639-1648, October 2019
  Automatic Diagnosis of Cardiac Arrhythmia in Electrocardiograms via Multigranulation Computing [Paper and Bib]
     Fenghuan Li, Kehai Chen*, Jie Ling, Yinwei Zhan, and Gunasekaran Manogaran
     Applied Soft Computing (ASC), Volume 80, Pages 400-413, July 2019

2018
  Syntax-Directed Attention for Neural Machine Translation [Paper and Bib][Poster]
     Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao
     The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), New Orleans, Lousiana, USA, February 2018
  Sentence Selection and Weighting for Neural Machine Translation Domain Adaptation [Paper and Bib]
     Rui Wang, Masao Utiyama, Andrew Finch, Lemao Liu, Kehai Chen, and Eiichro Sumita
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 26, no. 10, pp. 1727-1741, October 2018
  Syntax-Based Context Representation for Statistical Machine Translation [Paper and Bib]
     Kehai Chen, Tiejun Zhao, and Muyun Yang
     IEICE Transactions on Information and Systems, vol. E101.D, no. 12, pp. 3226-3237, December 2018
  A Neural Approach to Source Dependency-Based Context Model for Statistical Machine Translation [Paper and Bib]
     Kehai Chen, Tiejun Zhao, Muyun Yang, Lemao Liu, Akihiro Tamura, Rui Wang, Masao Utiyama, and Eiichro Sumita
     IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), vol. 26, no. 2, pp. 266-280, February 2018

2017
  Context-Aware Smoothing for Neural Machine Translation [Paper and Bib][Slides]
     Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao
     The 8th International Joint Conference on Natural Language Processing (IJCNLP), Chinese Taipei, November 2017
  Neural Machine Translation with Source Dependency Representation [Paper and Bib][Slides]
     Kehai Chen, Rui Wang, Masao Utiyama, Lemao Liu, Akihiro Tamura, Eiichiro Sumita, and Tiejun Zhao
     The 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark, September 2017
  Instance Weighting for Neural Machine Translation Domain Adaptation [Paper and Bib][Poster]
     Rui Wang, Masao Utiyama, Lemao Liu, Kehai Chen, and Eiichro Sumita
     The 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark, September 2017
  Translation Prediction with Source Dependency-Based Context Representation [Paper and Bib][Poster]
     Kehai Chen, Tiejun Zhao, Muyun Yang, and Lemao Liu
     The Thirty-First AAAI Conference on Artificial Intelligence (AAAI), San Francisco, California, USA, February 2017

Academic Services

Program Committee Member
2023: ICLR, AAAI, ACL, IJCAI, IJCNLP-AACL (Workshop Co-Chair), CCMT (Forum Co-Chair), CCL (Area Chair), NeurIPS
2022: ICLR, AAAI (Senior Program Committee), IJCAI-ECAI, ACL (Area Chair), CCMT (Publicity Co-Chair), NeurIPS, EMNLP, COLING, NLPCC, AACL-IJCNLP (Area Chair)
2021: ACL-IJCNLP, NeurIPS, AAAI (Senior Program Committee), EMNLP, NAACL-HLT, CoNLL, ICASSP, NLPCC, EACL, CCL, CCMT
2020: ACL, NeurIPS, AAAI, EMNLP, COLING, NLPCC, AACL-IJCNLP, CCL, CCMT
2019: AAAI, EMNLP, NAACL-HLT, CCL
2018: EMNLP
2017: ACL

Journal Reviewer
ACL Rolling Reviewer (ARR)
IEEE Trans. PAMI; IEEE Trans. on NNLS; IEEE Trans. on KDE, IEEE/ACM Trans on ASLP; IEEE Trans. on II; ACM Trans on ALLIP
ACM Computing Surveys; Artificial Intelligence Review
Information Sciences; Natural Language Engineering; Neurocomputing; Neural Computing & Applications
计算机学报; 自动化学报

Interns @NICT

   Wang Xu (Ph.D. Student, HIT, China, 2020.7~2021.11)
   Chaoqun Duan (Ph.D. Student, HIT, China, 2019.06~2020.09)
   Zhuosheng Zhang (Ph.D. Student, SJTU, China, 2019.06-2020.07)
   Haipeng Sun (Ph.D. Student, HIT, China, 2018.11-2020.04)

Last Updated May 2023 | Designed by Kehai Chen