时间：2024年10月15日（周二）10:30-12:00

Time:10:30-12:00, Tuesday,October 15, 2024

地点：西湖大学云谷校区E10-201

Venue：E10-201, Yungu Campus

主持人: 西湖大学工学院讲席教授 Mohamad Sawan

Host:Mohamad Sawan, Chair Professor of School of Engineering, Westlake University

主讲嘉宾/Speaker：

张岳博士

西湖大学终身教授

主讲人简介/Biography:

Yue Zhang is a tenured Professor at betway必威棋牌登录 His research interests include NLP and its underlying machine learning algorithms. His major contributions to the field include psycholinguistically motivated machine learning algorithm, learning-guided beam search for structured prediction, pioneering neural NLP models including graph LSTM, and OOD generalization for NLP. He authored the Cambridge University Press book ``Natural Language Processing -- a Machine Learning Perspective''. He is the PC co-chair for CCL 2020 and EMNLP 2022, and action editor for Transactions for ACL. He also served as associate editor for IEEE/ACM Transactions of Audio Speech and Language Processing (TASLP), ACM Transactions on Asian and Low-Resource Languages (TALLIP), IEEE Transactions on Big Data (TBD) and Computer, Speech and Language (CSL). He won the best paper awards of IALP 2017 and COLING 2018, best paper honorable mention of SemEval 2020, and best paper nomination for ACL 2018 and ACL 2023.

讲座摘要/Abstract:

In this talk, I will discuss linguistic reasoning, and the capabilities of formal logic reasoning for large language models (LLMs). I will discuss the difficulty of learning formal reasoning from empirical risk minimization, and discuss a perspective to this problem from causal learning theory. I will discuss causal features and confounders, and show how learning confounders can lead to low out-of-distribution generalization performance. Then I will discuss two general methods to address the issue, including a data-centric method and a model-centric method, introducing several recent works using both methods.

讲座联系人/Contact:

Yitian(Claire) Zhang

zhangyitian@westlake.edu.cn

Fangyuan(Tiffany) Tian

tianfangyuan@westlake.edu.cn