Joint Inference Approaches for Event Coreference Resolution
演讲者： Ruihong Huang
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 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), distinct contexts and long distances between coreferential event mentions.
In this talk, I will first present our recent work on event coreference resolution that tackles the conundrum and gradually builds event clusters both within a document and across documents by exploiting inter-dependencies among event mentions in an iterative joint inference approach. Then, I will further present our new work that focuses on in-document event coreference resolution and extensively models correlations between event coreference chains and document topic structures by using an Integer Linear Programming based joint inference approach.
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 TAMU in Fall 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.