home · mobile · calendar · defenses · 2005-2006 · 

Thesis Defense - Pradhan

Robust Semantic Role Labeling
Computer Science PhD Candidate
MSSC E-269

The natural language processing community has recently experienced a growth of interest in domain independent semantic role labeling -- the process of assigning a Who did What to Whom, When, Where, Why, How etc. structure to plain text. This process entails identifying groups of words in a sentence that represent these semantic arguments and assigning specific labels to them. It could play a key role in NLP tasks like Information Extraction, Question Answering and Summarization. This thesis focuses on: i) improving labeling performance on the standard data sets on which others have previously reported results, by modifying the system architecture as well as incorporating novel features, ii) extending this work to label arguments of nominal predicates, which also play an important role in deciphering the semantics of a passage, and iii) investigating methods to improve the robustness of the labeler across different types of corpora.

Committee: Wayne Ward, Research Professor (Chair)
James Martin, Associate Professor
Daniel Jurafsky, Stanford University
Martha Palmer, Associate Professor
Gregory Grudic, Assistant Professor

This defense will be held at the Center for Spoken Language Research in the Marine Street Science Center on the East Campus at 3215 Marine Street.

Department of Computer Science
University of Colorado Boulder
Boulder, CO 80309-0430 USA
May 5, 2012 (14:20)