The semantics of role labeling

Srikumar, Vivek

Permalink

https://hdl.handle.net/2142/44359 Copy

Description

Title

The semantics of role labeling

Author(s)

Srikumar, Vivek

Issue Date

2013-05-24T22:08:56Z

Director of Research (if dissertation) or Advisor (if thesis)

Roth, Dan

Doctoral Committee Chair(s)

Roth, Dan

Committee Member(s)

• DeJong, Gerald F.
• Hockenmaier, Julia C.
• Palmer, Martha

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• Natural Language Processing
• Machine Learning
• Semantic Role Labeling
• Text Processing
• Structured Learning
• Structured Inference
• Semantic Relations

Abstract

The problem of ascribing a semantic representation to text is an important one that can help text understanding problems like textual entailment. In this thesis, we address the problem of assigning a shallow semantic representation to text. This problem is traditionally studied in the context of verbs and their nominalizations. We propose to extend the task to go beyond verbs and nominalizations to include other linguistic constructions such as commas and prepositions We develop an ontology of predicate-argument relations that commas and prepositions express in text. Just like the verb and nominal semantic role labeling schemes, the relations we propose are domain independent. For these two classes of phenomena, we introduce new corpora where these relations are annotated. From the machine learning perspective, learning to predicting these relations is a structured learning problem. However, we only have the small (for commas) or partially annotated (for prepositions) datasets. To predict the new relations, we show that using linguistic knowledge and information about output structure can bias the learning to build robust models. Finally, we observe that the relations expressed by the various phenomena interact with each other by constraining each others' output. We show that we can take advantage of these inter-dependencies by enforcing coherence between their predictions. By constraining inference using linguistic knowledge, we can improve relation prediction performance.

Graduation Semester

2013-05

Permalink

http://hdl.handle.net/2142/44359

Copyright and License Information

Copyright 2013 Vivek Srikumar

Owning Collections