Event Info This research seminar is organized by Singtel-NTU Corporate Lab (SCALE@NTU). Invited Talk: On Robustifying AI with Data Intelligence Large-scale language models have enabled super-human fluency in diverse NLP tasks, potentially revolutionizing human-machine and human-human interactions. However, their limited robustness is observed to be a major obstacle and cannot be overcome by increasing scale. This talk argues current norms of model training are too constrained and lead to over-confident models, then discusses our recent work, showing how knowledge such as causality and evidentiality can enrich interactions towards robust training of NLP models. A longer version of this talk (with older results) can be found as EDBT 2022 keynote. Speaker: Prof. Seung-won Hwang, Computer Science and Engineering, Seoul National University Seung-won Hwang is a Professor of Computer Science and Engineering at Seoul National University. Prior to joining SNU, she has been a tenured faculty at POSTECH and Yonsei University, after her PhD from UIUC. Her research contributions lie at the intersection of NLP, Information Retrieval, and Data Intelligence, published as 100+ top-tier conference papers and transferred to products from industry collaborations, recognized by Microsoft Research Outstanding Collaborator Award. More details can be found at http://seungwonh.github.io.
Registration for this event has closed. |