Bill Yuchen Lin
commonsense reasoning
dataset
information extraction
multilingual
multi-task learning
text generation
pre-training
benchmark
commonsense
reasoning
continual learning
cross-lingual
named entity recognition
dialogue systems
transfer learning
19
presentations
123
number of views
SHORT BIO
Yuchen Lin is a final-year Ph.D. candidate in Computer Science at the University of Southern California. He works with Prof. Xiang Ren at the Intelligence and Knowledge Discovery Research Lab (USC-INK). He is interested in developing intelligent systems that can demonstrate a deep understanding of the world with common-sense knowledge and reasoning ability by teaching machines to think, talk, and act as humans do. To this end, his research aims to integrate techniques of information extraction, knowledge graphs, robustness, cross-task generalization, etc. Besides, he is also interested in continual learning and federated learning topics.
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, advised by Prof. Kenny Zhu. He was an intern at Facebook AI Research (FAIR) (2021 with Scott Yih), Google AI (2020 with William Cohen, 2019 with Sandeep Tata), and Microsoft Research Asia (2017-2018). He has been serving as the PC members (i.e., reviewers) for ARR (*CL conference), ICML, NeurIPS, ICLR, AAAI, etc. He co-organizes several workshops (e.g., CSKB, CSRR, and FL4NLP) and will give a tutorial on knowledge-augmented NLP at ACL 2022.
Presentations
Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning
Tejas Srinivasan and 6 other authors
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning | VIDEO
Ximing Lu and 16 other authors
AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction
Dong-Ho Lee and 8 other authors
On Grounded Planning for Embodied Tasks with Language Models
Bill Yuchen Lin and 5 other authors
Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality
Pei Zhou and 6 other authors
On the Robustness of Reading Comprehension Models to Entity Renaming
Jun Yan and 5 other authors
On Continual Model Refinement in Out-of-Distribution Data Streams
Bill Yuchen Lin and 6 other authors
Knowledge-Augmented Methods for Natural Language Processing: Motivation and Introduction of Knowledge in NLP
Chenguang Zhu and 5 other authors
Knowledge-Augmented Methods for Natural Language Processing: Commonsense Knowledge and Reasoning for NLP
Xiang Ren and 1 other author
Knowledge-Augmented Methods for Natural Language Processing Part 1
Chenguang Zhu and 5 other authors
RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
Bill Yuchen Lin and 4 other authors
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
Qinyuan Ye and 2 other authors
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms
Pei Zhou and 6 other authors
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms
Pei Zhou and 6 other authors
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
Qinyuan Ye and 2 other authors
Probing Commonsense Explanation in Dialogue Response Generation
Pei Zhou and 5 other authors