Event Coreference Resolution by Iteratively Unfolding Inter-dependencies Among Events

When: Friday, April 13, 2018
Where: PGH 232
Time: 11:00 AM

Speaker: Ruihong Huang

Host: Dr. Thamar Solorio

Recognizing all references to the same event within a document
as well as across documents is vital for information aggregation, storyline generation and many NLP applications, such as event detection and tracking, question answering and text summarization. While it can be more risky and require additional evidence to link event mentions from two distinct documents, resolving event coreference links within a document is equally challenging due to dissimilar event word forms, incomplete event arguments (e.g., event participants, time and location) and distinct contexts. In this talk, I will present our recent work on event coreference resolution that tackles the conundrum and gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across event chains in an iterative joint inference approach. I will then briefly discuss various applications of event coreference resolution and the future directions.

Bio:

Ruihong Huang is an Assistant Professor in the Computer Science and Engineering Department at Texas A&M University, College Station. Dr. Huang received her PhD in computer science at the University of Utah. She joined Texas A&M University in the Fall of 2015 after she completed a Postdoc at Stanford University.
 Her research is mainly on computational linguistics and machine learning, with special research interests on information extraction, discourse and semantics. Her research spans from extracting propositional facts from texts to studying extra-propositional aspects of meanings and various subjectivities.