Title

SW-AG: Local Context Matching For English Substitution

Document Type

Conference Proceeding

Publication Date

2007

Published In

SemEval '07 Proceedings Of The 4th International Workshop On Semantic Evaluations

Abstract

We present two systems that pick the ten most appropriate substitutes for a marked word in a test sentence. The first system scores candidates based on how frequently their local contexts match that of the marked word. The second system, an enhancement to the first, incorporates cosine similarity using unigram features. The core of both systems bypasses intermediate sense selection. Our results show that a knowledge-light, direct method for scoring potential replacements is viable.

Published By

Association For Computational Linguistics

Conference

4th International Workshop On Semantic Evaluations

Conference Dates

June 23-24, 2007

Conference Location

Prague, Czech Republic