CS Colloquium: Muhao Chen
Speaker: Muhao Chen
Date: Friday, February 10th, 2023
Time: 3:00 - 4:00 pm
Location: HFH 1132
Host: Shiyu Chang
Title: Robust and Indirectly Supervised Information Extraction
Abstract:
Information extraction (IE) refers to the process of automatically determining the concepts and relations present in natural language text. It is the fundamental task for evaluating a machine's ability to understand natural language, as well as the essential step for acquiring structured knowledge representation required by knowledge-driven AI systems. Despite the importance, Obtaining direct supervision for IE tasks, however, is challenging due to the difficulty in locating complex structures in long documents by expert annotators. Therefore, a robust and accountable IE model has to be achievable with minimal and imperfect supervision. Towards this mission, this talk presents recent advances of machine learning and inference technologies that (i) grant robustness against noise and perturbation, (ii) prevent systematic errors caused by spurious correlations, and (iii) provide indirect supervision for label-efficient and logically consistent IE.
Bio:
Muhao Chen is an Assistant Research Professor of Computer Science at USC, and the director of the USC Language Understanding and Knowledge Acquisition (LUKA) Lab (https://luka-group.github.io/