Investigating lexical substitution scoring for subtitle generation

Oren Glickman, Ido Dagan, Mikaela Keller, Samy Bengio, Walter Daelemans

Research output: Contribution to conferencePaperpeer-review

6 Scopus citations

Abstract

This paper investigates an isolated setting of the lexical substitution task of replacing words with their synonyms. In particular, we examine this problem in the setting of subtitle generation and evaluate state of the art scoring methods that predict the validity of a given substitution. The paper evaluates two context independent models and two contextual models. The major findings suggest that distributional similarity provides a useful complementary estimate for the likelihood that two Wordnet synonyms are indeed substitutable, while proper modeling of contextual constraints is still a challenging task for future research.

Original languageEnglish
Pages45-52
Number of pages8
StatePublished - 2006
Event10th Conference on Computational Natural Language Learning, CoNLL 2006 - New York City, United States
Duration: 8 Jun 20069 Jun 2006

Conference

Conference10th Conference on Computational Natural Language Learning, CoNLL 2006
Country/TerritoryUnited States
CityNew York City
Period8/06/069/06/06

Bibliographical note

Publisher Copyright:
© 2006 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'Investigating lexical substitution scoring for subtitle generation'. Together they form a unique fingerprint.

Cite this