Accession Number:

ADA470421

Title:

Generalizing Semantic Role Annotations Across Syntactically Similar Verbs

Descriptive Note:

Corporate Author:

UNIVERSITY OF SOUTHERN CALIFORNIA MARINA DEL REY CA INST FOR CREATIVE TECHNOLOGIES

Personal Author(s):

Report Date:

2007-06-01

Pagination or Media Count:

9.0

Abstract:

Large corpora of parsed sentences with semantic role labels e.g. PropBank provide training data for use in the creation of high-performance automatic semantic role labeling systems. Despite the size of these corpora, individual verbs or rolesets often have only a handful of instances in these corpora, and only a fraction of English verbs have even a single annotation. In this paper, we describe an approach for dealing with this sparse data problem, enabling accurate semantic role labeling for novel verbs rolesets with only a single training example. Our approach involves the identification of syntactically similar verbs found in Prop-Bank, the alignment of arguments in their corresponding rolesets, and the use of their corresponding annotations in Prop-Bank as surrogate training data.

Subject Categories:

  • Linguistics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE