Training an integrated sentence planner on user dialogue

Brian McMahan, Matthew Stone

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

Abstract

An appealing methodology for natural language generation in dialogue systems is to train the system to match a target corpus. We show how users can provide such a corpus as a natural side effect of interacting with a prototype system, when the system uses mixed-initiative interaction and a reversible architecture to cover a domain familiar to users. We experiment with integrated problems of sentence planning and realization in a referential communication task. Our model learns general and context-sensitive patterns to choose descriptive content, vocabulary, syntax and function words, and improves string match with user utterances to 85.8% from a handcrafted baseline of 54.4%.

Original languageEnglish (US)
Title of host publicationSIGDIAL 2013 - 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages31-40
Number of pages10
ISBN (Electronic)9781937284954
StatePublished - 2013
Event14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013 - Metz, France
Duration: Aug 22 2013Aug 24 2013

Publication series

NameSIGDIAL 2013 - 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Proceedings of the Conference

Other

Other14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013
CountryFrance
CityMetz
Period8/22/138/24/13

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Modeling and Simulation
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Training an integrated sentence planner on user dialogue'. Together they form a unique fingerprint.

Cite this