- Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey. ACM Computing Surveys 56(2), 1-40.
- Generating Labeled Data for Relation Extraction: A Meta Learning Approach with Joint GPT-2 Training. In Findings of ACL 2023.
- Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning. In Proceedings of ACL 2023.
- Cross-Document Event Coreference Resolution: Instruct Humans or Instruct GPT?. In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL) 2023.
- Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction. To appear at the 2nd HCI + NLP Workshop at NAACL-HLT 2022.
Research Experience
- 2025/07-Present: Distinguished Scientist/VP, Thomson Reuters Labs, working on Generative and Agentic AI.
- 2022/8-2025/05: Principal Applied Scientist, Amazon AWS AI Labs, building generative-AI powered services (Amazon Q), Large Language Models (Amazon Bedrock/Titan), and NLP services (Amazon Comprehend).
- 2013/7-2022/08: Raytheon Engineering Fellow / Lead Scientist, Principal Investigator (PI), Head of Text group, Raytheon BBN Technologies, led a group to develop novel NLP tools and associated ML models.
- 2012/6-2012/9: Research Intern, DeepQA team, IBM T.J. Watson Research Center, research in Deep Question Answering for Watson.
- 2011/6-2011/9: Research Intern, Web Intelligence (WIT) Group, Microsoft Research Asia, research in open-domain information extraction.
- 2006-2007: Part-time Research Intern, Internet Media (IM) Group, Microsoft Research Asia, Active Learning on Video Annotation.
- 2005/7-2005/9: Software Engineer Intern, Baidu.com Inc.
Education
Ph.D. in Computer Science, Courant Institute of Mathematical Sciences, New York University (2008.9-2013.5, M.S. received in 2010), advised by Prof. Ralph Grishman; M.S. in Computer Science, Peking University (received in Jul. 2008), advised by Prof. Yafei Dai and Prof. Xiaoming Li, worked in Parallel and Distributed Computing area; B.S. in Computer Science and B.A. in Economics (double major), Peking University (both received in Jul. 2005).
Background
Research interests are in the areas of Natural Language Processing (NLP), Machine Learning (ML), and systems and architectural design for large-scale text understanding, mining and retrieval.
Miscellany
Teaching Natural Language Processing at Tufts University Computer Science department.