Hui Wan

Dr. Wan is a research scientist at IBM Research AI, working on Natural Language Processing, Deep Learning, and Machine Learning.

Her recent research projects are in Conversational AI, Generative AI, Neural Information Retrieval, Question Answering, and other NLP areas. During her Ph.D. study at Stony Brook University, her work was mainly on Knowledge Representation and Reasoning with uncertainty, Deductive Databases, and Semantic Web.

Dr. Wan is enthusiastic about advancing the front of NLP and AI progress and scaling up to solve real-world problems. She is the recipient of IBM Outstanding Technical Achievement Award.

Come check out our workshop DialDoc@ACL2023 !

Our workshop DialDoc@ACL2022 and the Shared Task .

Education

Ph.D., Computer Science, Stony Brook University
Master, Computer Science, Chinese Academy of Sciences
Bachelor, Computer Science, University of Science and Technology of China, School of the Gifted Young

Publications

Fast and Light-weight Answer Text Retrieval in Dialogue Systems

Hui Wan, Siva Sankalp Patel, J William Murdock, Saloni Potdar, Sachindra Joshi.

Accepted at North American Chapter of the Association for Computational Linguistics (NAACL) Industry Track, 2022.

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

Pengshan Cai, Hui Wan, Fei Liu, Mo Yu, Hong Yu, Sachindra Joshi.

Accepted at North American Chapter of the Association for Computational Linguistics (NAACL), 2022.

MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents

Song Feng, Siva Sankalp Patel, Hui Wan, Sachindra Joshi.

Empirical Methods in Natural Language Processing (EMNLP), Punta Cana, Dominican Republic, 2021.

Does Structure Matter? Encoding Documents for Machine Reading Comprehension

Hui Wan, Song Feng, Chulaka Gunasekara, Siva Sankalp Patel, Sachindra Joshi, Luis A. Lastras.

North American Chapter of the Association for Computational Linguistics (NAACL), online, 2021.

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks

Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji.

North American Chapter of the Association for Computational Linguistics (NAACL), online, 2021.

doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset

Song Feng, Hui Wan, Chulaka Gunasekara, Siva Sankalp Patel, Sachindra Joshi, Luis A. Lastras.

Empirical Methods in Natural Language Processing (EMNLP), online, 2020.

Multi-task Learning with Multi-head Attention for Multi-choice Reading Comprehension

Hui Wan

arXiv:2003.04992, 2020. (DREAM Leaderboard top position.)

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

Tahira Naseem, Abhishek Shah, Hui Wan, Radu Florian, Salim Roukos, Miguel Ballesteros.

Annual Conference of the Association for Computational Linguistics (ACL), Florence, Italy, 2019.

IBM Research at the CoNLL 2018 Shared Task on Multilingual Parsing

Hui Wan, Tahira Naseem, Young-Suk Lee, Vittorio Castelli, Miguel Ballesteros.

SIGNLL Conference on Computational Natural Language Learning (CoNLL), Brussels, Belgium, 2018.

Measuring Graph Proximity with Blink Model

Haifeng Qian, Hui Wan, Mark N. Wegman, Luis A. Lastras, Ruchir Puri.

International Workshop on Mining and Learning with Graphs (a KDD workshop), San Francisco, USA, 2016.

Defeasibility in Answer Set Programs with Defaults and Argumentation Rules

Hui Wan, Michael Kifer, Benjamin N. Grosof.

Semantic Web Journal, volume 6, pp. 81-98, 2015.

Defeasibility in Answer Set Programs via Argumentation Theories

Hui Wan, Michael Kifer, Benjamin N. Grosof.

International Conference on Web Reasoning and Rule Systems (RR), Bressanone/Brixen, Italy, 2010.

Logic Programming with Defaults and Argumentation Theories

Hui Wan, Benjamin Grosof, Michael Kifer, Paul Fodor, Senlin Liang.

International Conference on Logic Programming (ICLP), Pasadena, California, USA, 2009.

Belief Logic Programming: Uncertainty Reasoning with Correlation of Evidence

Hui Wan, Michael Kifer.

International Conference on Logic Programming and Nonmonotonic Reasoning (LPNMR), Potsdam, Germany, 2009.

Query Answering in Belief Logic Programming

Hui Wan, Michael Kifer.

International Conference on Scalable Uncertainty Management (SUM), Washington DC, USA, 2009.

Belief Logic Programming with Cyclic Dependencies

Hui Wan

International Conference on Web Reasoning and Rule Systems (RR), Chantilly, Virginia, USA, 2009.

OpenRuleBench: An Analysis of the Performance of Rule Engines

Senlin Liang, Paul Fodor, Hui Wan, Michael Kifer.

18th International World Wide Web Conference (WWW), Madrid, Spain, 2009.

Personalized Tag Recommendations via Social Network and Content-based Similarity Metrics

Andrew Byde, Hui Wan, Steve Cayzer.

International Conference on Weblogs and Social Media (ICWSM), Boulder, Colorado, USA, 2007.