Tianyu Gao 高天宇

Hi! I am Tianyu Gao, a third-year PhD student at Princeton University, advised by Prof. Danqi Chen. I am also a proud member of the Princeton NLP group. Before Princeton, I received my bachelor's degree at Tsinghua University. During my time at Tsinghua, I was a member of THUNLP and was advised by Prof. Zhiyuan Liu. Here is my CV.


Find me on Twitter, Google Scholar, and Github!


Email: tianyug@cs.princeton.edu

Research

My research interests lie within the intersection of natural language processing and machine learning. At the current stage, I am specifically interested in pre-trained language models, few-shot learning, contrastive learning, information extraction, etc.

Contact me

You can reach out to me by email (I'm usually very responsive on email). I also hold a weekly research office hour on Zoom. If you are a Princeton undergrad/grad student interested in working with me, or a researcher wanting to catch up, feel free to sign up :)

Highlighted Publications

Please refer to my publications for the full list.

Alexander Wettig*, Tianyu Gao*, Zexuan Zhong, Danqi Chen (* indicates equal contribution)
Should You Mask 15% in Masked Language Modeling?
Preprint, 2022 pdf code

Huihan Li*, Tianyu Gao*, Manan Goenka, Danqi Chen (* indicates equal contribution)
Ditch the Gold Standard: Re-evaluating Conversational Question Answering
Proceedings of ACL, 2022 (Outstanding Paper Award) pdf code

Tianyu Gao*, Xingcheng Yao*, Danqi Chen (* indicates equal contribution)
SimCSE: Simple Contrastive Learning of Sentence Embeddings
Proceedings of EMNLP, 2021 pdf code

Tianyu Gao*, Adam Fisch*, Danqi Chen (* indicates equal contribution)
Making Pre-trained Language Models Better Few-shot Learners
Proceedings of ACL, 2021 pdf code

Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
Proceedings of EMNLP (Short Paper), 2019 pdf code