[Adapt] Visit and talk by William Wang from UC Santa Barbara

Kenny Zhu kzhu at cs.sjtu.edu.cn
Mon Sep 17 08:19:43 CST 2018

Hi guys,

Please attend this talk to chat with William. All graduate students who don’t have classes at that time must attend.



Title: Deep Reinforcement Learning for NLP: Methods and Observations.

Speaker: William Wang (Director of UC Santa Barbara NLP Group)

Time: Thursday, Sept 20, 10:30 AM

Venue: 03-412


Learning to reason and understand human language is a fundamental problem in Artificial Intelligence (AI). While supervised deep learning methods have made steady progress in low-level perception tasks, in contrast, how machines can learn and reason in weakly-supervised settings are still largely unknown.

With the recent advances of deep reinforcement learning (DRL), now is a good opportunity to revisit this topic. The core research question that I will address in this talk is the following: how can we design weakly-supervised statistical learning and inference methods to operate over rich language and knowledge representations? In this talk, I will discuss three practical research directions for DRL in real-world NLP problems by showcasing our recent studies in this area: (1) Reinforced Semi-Supervised Learning. Given large amount of unlabeled data, can DRL help select high-quality unlabeled examples for weakly-supervised learning? (2) Language Generation. What is the role of DRL for generation problems? How to generate more structured NL sentences with DRL? How to improve sample efficiency and learn the rewards? (3) Knowledge Graph Reasoning. Can we teach machines to reason on knowledge graphs with DRL agents and unleash the power of dark data? Finally, I will conclude and introduce other exciting research areas at UCSB’s Natural Language Processing Lab.

Bio: William Wang is the Director of UC Santa Barbara's Natural Language Processing group (http://nlp.cs.ucsb.edu/ <http://nlp.cs.ucsb.edu/>) and an Assistant Professor in the Department of Computer Science at the University of California, Santa Barbara. He received his PhD from School of Computer Science, Carnegie Mellon University. He has broad interests in machine learning approaches to data science, including statistical relational learning, information extraction, computational social science, speech, and vision. He has published more than 60 papers at leading NLP/AI/ML conferences and journals, and received best paper awards (or nominations) at ASRU 2013, CIKM 2013, and EMNLP 2015, a best reviewer award at NAACL 2015, a U.S. Government Young Faculty Award in 2018, two IBM Faculty Awards in 2017 and 2018, a Facebook Research Award in 2018, an Adobe Research Award in 2018, and the Richard King Mellon Presidential Fellowship in 2011. He served as an Area Chair for NAACL, ACL, EMNLP, and AAAI. He is an alumnus of Columbia University, Yahoo! Labs, Microsoft Research Redmond, and University of Southern California. In addition to research, William enjoys writing scientific articles that impact the broader online community: his microblog @王威廉 has 100,000+ followers and more than 2,000,000 views each month. His work and opinions appear at major international tech media outlets such as Wired, VICE, Fast Company, the Next Web, the Brookings Institution, and Mental Floss.

Picture: http://www.cs.ucsb.edu/~william/profile.png <http://www.cs.ucsb.edu/~william/profile.png>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20180917/7b083e33/attachment.html>

More information about the Adapt mailing list