Link Search Menu Expand Document

(Bill) Yuchen Lin, PhD Candidate

Bill Yuchen Lin

News Experience Papers Resources Misc.

Yuchen Lin is a Ph.D. candidate in Computer Science at the University of Southern California, working with Prof. Xiang Ren at the Intelligence and Knowledge Discovery Research Lab (USC-INK). He is generally interested in developing intelligent systems that demonstrate a deep understanding of the world with common-sense knowledge and reasoning ability — teaching machines to think 🤔, talk 💬, act 🦾 with common sense as humans. To this end, his research aims to integrate information extraction, knowledge graphs, logical reasoning, graph neural networks, explanations, robustness, etc. Apart from that, he is also interested in cross-task generalization (i.e., meta-learning, continual learning) and federated learning in the NLP domain. He mainly publishes (as Bill Yuchen Lin) and serves as Program Committee members for ACL, EMNLP, NAACL, ICLR, AAAI, etc.

Previously, he got his bachelor’s degree from the IEEE Honored Class at Shanghai Jiao Tong University (2014-2018) and won the Best Thesis Award (1% in SJTU) under the supervision of Prof. Kenny Zhu. He worked as a research intern at Google AI (2020 summer with William Cohen, 2019 summer with Sandeep Tata) and Microsoft Research Asia (2017-2018). He will intern at Facebook AI Research (FAIR) with Scott Yih in 2021 summer.

All Papers Twitter Google Scholar INK Lab

  • Email: yuchen [dot] lin [at] usc [dot] edu
  • Resume/CV: Please email me for the latest pdf version.

News (in 2021)

07-06 Vered, Antoine, Lorraine and I are organizing an AKBC workshop on commonsense and KBs (CSKB@AKBC21). Please consider submitting your (published/unpublished) work there! We have some stellar speakers and panelists. Check it here.

Our paper “AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction” won the Best Paper Award at NAACL21 TrustNLP workshop!


Selected as one of the AI Rising Stars in Chinese Students by Baidu Research.


We have two full papers on commonsense reasoning accepted to ACL2021 (1 long + 1 findings): X-CSR and RiddleSense!

04-17 Releasing FedNLP-- A research platform for Federated Learning in NLP. [Tweet]
04-17 A new arXiv preprint with Qinyuan, CʀᴏssFɪᴛ: A Few-shot Learning Challenge for Cross-Task Generalization in NLP. [Tweet]
04-07 Our works on commonsense reasoning got covered by an article on Communications of the ACM: The Best of NLP.
03-15 Finally passed my qual exam and officially became a PhD Candidate now. [Slides]
03-10 My Google internship work about open-ended commonsense reasoning is accepted to NAACL21. Check our website here.
01-25 Releasing Rebiber, a simple tool to fix outdated arXiv citations! [Twitter]
01-20 Check out our ICLR 2021 paper on pre-training text-to-text transformers for common sense.