I²R Staff Profile

Liu Zhengyuan is a Lead Research Engineer at A*STAR Institute for Infocomm Research (A*STAR I²R). Working extensively in the field of AI and Natural Language Processing (NLP), Zhengyuan takes up the role of project co-PI and tech lead, transforming novel research ideas into practical technical solutions, works closely with various collaborators on multiple interdisciplinary projects, and has made core contributions to more than 10 project-related software IPs and technical disclosures. He has been a mentor to junior research staffs and PhD students as co-supervisor, providing academic and technical guidance. Prior to joining A*STAR I²R, Zhengyuan worked as a Research and Development Engineer and Team Leader on Big Data and Cloud Computing at Huawei Chengdu Institute from 2012 to 2017.

He obtained an M.S. degree in Information Systems from Nanyang Technological University, Singapore, in 2018 and a B.S. degree in Computer Science from Sichuan University, China, in 2012. He has published 20+ research papers as the first and core author in top-tier AI and Natural Language Processing conferences including ACL, NAACL, EMNLP, COLING, SIGDIAL, ICASSP, and Interspeech. He serves as the program committee and reviewer in conferences including NeurIPS, ICLR, and ACL, and journals including IEEE TASLP, ACM CSUR, Neurocomputing, Pattern Recognition, Knowledge-based Systems, and Computer Speech & Language. He also serves as the conference session chair in ICASSP and Interspeech. He has been elected as the IEEE senior member for his significant professional achievement, and won the Best Paper Award at SIGDIAL 2021.

Professional and Academic Engagements

  • Senior Member of IEEE.
  • Member of ACL, ISCA, and AAAI.
  • Session chair for INTERSPEECH 2022 (Incheon, Korea), and ICASSP 2023 (Rhodes, Greece)
  • Program Committee and Reviewer for top-tier conferences:
    • Year 2022: ACL 2022, NAACL 2022, EMNLP 2022, COLING 2022, ICASSP 2022.
    • Year 2021: ACL 2021, NAACL 2021, EMNLP 2021, ML4H@NeurIPS 2021, ICASSP 2021.
    • Year 2020: ACL 2020, EMNLP 2020, COLING 2020, NeurIPS 2020, ML4H@NeurIPS 2020.
    • Year 2019: EMNLP 2019, ML4H@NeurIPS 2019.
  • Reviewer for top-tier journals:
    • IEEE/ACM Transactions on Audio Speech and Language Processing, Neurocomputing, Pattern Recognition, Knowledge-based Systems, Computer Speech & Language.

Publications

  • Zhengyuan Liu and Nancy F. Chen. “Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Information”. In Proceedings of the ICASSP 2023.
  • Zhengyuan Liu and Nancy F. Chen. “Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer”. In Findings of the NAACL 2022.
  • Zhengyuan Liu, Shikang Ni, Ai Ti Aw, Nancy F. Chen. “Singlish Message Paraphrasing: A Joint Task of Creole Translation and Text Normalization”. In Proceedings of COLING 2022.
  • Zhengyuan Liu and Nancy F. Chen. “Entity-based De-noising Modeling for Controllable Dialogue Summarization”. In Proceedings of the SIGDIAL 2022.
  • Zhengyuan Liu and Nancy F. Chen. “Dynamic Sliding Window Modeling for Abstractive Meeting Summarization”. In Proceedings of the ISCA INTERSPEECH 2022.
  • Aksu, Taha, Zhengyuan Liu, Nancy F. Chen, and Min-Yen Kan. “N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking”. In Findings of the ACL 2022.
  • Zhengyuan Liu and Nancy F. Chen. “Controllable Neural Dialogue Summarization with Personal Named Entity Planning”. In Proceedings of the EMNLP 2021.
  • Zhengyuan Liu, Ke Shi, and Nancy F. Chen. “Coreference-Aware Dialogue Summarization”. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2021 Best Paper Award).
  • Zhengyuan Liu, Ke Shi, and Nancy F. Chen. “DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing”. In Proceedings of the EMNLP-CODI 2021.
  • Zhengyuan Liu and Nancy F. Chen. “Improving Multi-Party Dialogue Discourse Parsing via Domain Integration”. In Proceedings of the EMNLP-CODI 2021.
  • Ibrahim Taha Aksu, Zhengyuan Liu, Min-Yen Kan, Nancy F. Chen. “Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synthetic Text Generation with Domain Adaptation”. In Proceedings of the SIGDIAL 2021.
  • Zhengyuan Liu, Ke Shi, and Nancy F. Chen. “Multilingual Neural RST Discourse Parsing”. In Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020).
  • Zhengyuan Liu, Pavitra Krishnaswamy, Ai Ti Aw, and Nancy F. Chen. “Uncertainty Modeling for Machine Comprehension Systems using Efficient Bayesian Neural Networks”. In Proceedings of the COLING 2020.
  • Zhengyuan Liu, Ke Shi, and Nancy F. Chen. “Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization”. In Proceedings of the EMNLP 2020.
  • Zhengyuan Liu, Angela Ng, Sheldon Lee, Ai Ti Aw, and Nancy F. Chen. “Topic-aware pointer-generator networks for summarizing spoken conversations”. In Proceedings of the IEEE ASRU 2019.
  • Zhengyuan Liu, Nancy F. Chen. “Exploiting Discourse-Level Segmentation for Extractive Summarization”. In Proceedings of New Frontiers in Summarization@EMNLP 2019.
  • Zhengyuan Liu and Nancy F. Chen. “Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension”. In Proceedings of the ACL 2019.
  • Zhengyuan Liu, Hazel Lim, Farah Ain, ..., Wai Leng Chow, Nancy F. Chen. “Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring”. In Proceedings of the NAACL 2019.

A*STAR celebrates International Women's Day

A*STAR Women In Science

From groundbreaking discoveries to cutting-edge research, our researchers are empowering the next generation of female science, technology, engineering and mathematics (STEM) leaders.

Get inspired by our #WomeninSTEM