Dr. Chenguang Zhu

Chenguang Zhu   Principal Research Manager, Knowledge and Language Team, Microsoft Cognitive Services Research Group

Ph.D., Computer Science Department, Stanford University

M.S., Statistics Department, Stanford University

B. Eng., Computer Science & Technology Department, Tsinghua University

Email: A [at] B, where A=chezhu and B is microsoft.com

My Microsoft Homepage | Google Scholar | Books | Publications | Patents | Mentored Interns ]

Bio

 I am a Principal Research Manager in Microsoft Cognitive Service Research Group, leading the Knowledge and Language Team. Our team's research directions are 1) Knowledge-enhanced Language Model, 2) Summarization, 3) Few-shot and Prompt Learning, and 4) Multimodal Learning. We develop state-of-the-art deep learning technologies for both research and business applications. Our team has achieved first places in multiple NLP competitions, including achieving human parity in CommonsenseQA, HellaSwag and CoQA, 1st places in CommonGen, FEVER, ARC and SQuAD v1.0. Before Microsoft, I got my PhD in Computer Science Department, Stanford University and Bachelor in Computer Science from Yao Class, Tsinghua University.

News

 I organize the Distinguished Talk Series in Microsoft Cognitive Services Research Group. If you're interested in giving a talk, please contact me.

 Sep. 16, 2022: Chenguang Zhu gave a virtual talk "How We Achieved Human Parity in CommonsenseQA – Fusing Knowledge into Language Models" at ISI Seminar of USC. [ Slides | Video ]

 Sep. 15, 2022: We will organize The Workshop on Knowledge Augmented Methods for NLP (KnowledgeNLP-AAAI’23) at AAAI 2023. Welcome to submit!

 Sep. 14, 2022: 2 papers accepted at NeurIPS 2022.

 Jul. 15, 2022: I am one of the panelists at Deep Learning on Graphs Workshop for Natural Language Processing at NAACL 2022. [ Website | Recording (The panel starts at 2:00:30) ]

 May 22, 2022: Tutorial on Knowledge-Augmented Methods for Natural Language Processing at ACL 2022. [ Website | Video ]

 May 11, 2022: My team has achieved human parity on HellaSwag leaderboard.

 Apr. 26, 2022: My paper on Impossible Triangle in Pre-trained Language Model has been reported in multiple media. [ 机器之心 | AI科技评论 ]

 Apr. 20, 2022: 1 paper accepted at IJCAI 2022.

 Mar. 17, 2022: I gave a virtual talk "How We Achieved Human Parity in CommonsenseQA – Fusing Knowledge into Language Models" at NLP seminar at Stanford University. [ Slides ]

 Mar. 1, 2022: 2 papers accepted at CVPR 2022.

 Feb. 23, 2022: 9 papers accepted at ACL 2022.

 Feb. 18, 2022: I gave a virtual talk "How We Achieved Human Parity in CommonsenseQA – Fusing Knowledge into Language Models" at NLP and AI seminar at Georgia Tech. [ Slides ]

 Feb. 9, 2022: I gave a virtual talk "How We Achieved Human Parity in CommonsenseQA – Fusing Knowledge into Language Models" at BLISS seminar (Berkeley Laboratory for Information and System Sciences) at UC Berkeley. [ Slides ]


 My recent work covers:

Books

MRC_book_cover   Machine Reading Comprehension: Algorithm and Practice (Chinese Edition)

《机器阅读理解:算法与实践》

Chenguang Zhu

China Machine Press (机械工业出版社) , 2020.03

Top 5 Favorite IT Books (Artificial Intelligence) in 2020 by 51CTO.com [ Link ]
Amazon.com | China-pub | jd.com | dangdang.com | tmall.com | Amazon.cn ]

GitHub Code ]

        MRC_book_cover  Machine Reading Comprehension: Algorithm and Practice

Chenguang Zhu

Elsevier, 2021.04

Amazon.com | Google Books | Barnes & Noble ]

GitHub Code ]

Publication

Patents

Mentored Interns

I am very fortunate to have mentored and worked with talented interns.

Talks

Professional Services

Awards

Miscellaneous