Learning to interpret utterances using dialogue history

David De Vault, Matthew Stone

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

We describe a methodology for learning a disambiguation model for deep pragmatic interpretations in the context of situated task-oriented dialogue. The system accumulates training examples for ambiguity resolution by tracking the fates of alternative interpretations across dialogue, including subsequent clarificatory episodes initiated by the system itself. We illustrate with a case study building maximum entropy models over abductive interpretations in a referential communication task. The resulting model correctly resolves 81% of ambiguities left unresolved by an initial handcrafted baseline. A key innovation is that our method draws exclusively on a system's own skills and experience and requires no human annotation.

Original languageEnglish (US)
Title of host publicationEACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages184-192
Number of pages9
ISBN (Print)9781932432169
DOIs
StatePublished - 2009
Event12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009 - Athens, Greece
Duration: Mar 30 2009Apr 3 2009

Publication series

NameEACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings

Other

Other12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009
Country/TerritoryGreece
CityAthens
Period3/30/094/3/09

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Learning to interpret utterances using dialogue history'. Together they form a unique fingerprint.

Cite this