tucSage: Grammar Rule Induction for Spoken Dialogue Systems via Probabilistic Candidate Selection

Arodami Chorianopoulou, Georgia Athanasopoulou, Elias Iosif, Ioannis Klasinas, Alexandros Potamianos

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We describe the grammar induction system for Spoken Dialogue Systems (SDS) submitted to SemEval’14: Task 2. A statistical model is trained with a rich feature set and used for the selection of candidate rule fragments. Posterior probabilities produced by the fragment selection model are fused with estimates of phrase-level similarity based on lexical and contextual information. Domain and language portability are among the advantages of the proposed system that was experimentally validated for three thematically different domains in two languages.

Original languageEnglish
Title of host publication8th International Workshop on Semantic Evaluation, SemEval 2014 - co-located with the 25th International Conference on Computational Linguistics, COLING 2014, Proceedings
EditorsPreslav Nakov, Torsten Zesch
PublisherAssociation for Computational Linguistics (ACL)
Pages668-672
Number of pages5
ISBN (Electronic)9781941643242
Publication statusPublished - 2014
Externally publishedYes
Event8th International Workshop on Semantic Evaluation, SemEval 2014 - Dublin, Ireland
Duration: 23 Aug 201424 Aug 2014

Publication series

Name8th International Workshop on Semantic Evaluation, SemEval 2014 - co-located with the 25th International Conference on Computational Linguistics, COLING 2014, Proceedings

Conference

Conference8th International Workshop on Semantic Evaluation, SemEval 2014
Country/TerritoryIreland
CityDublin
Period23/08/1424/08/14

Fingerprint

Dive into the research topics of 'tucSage: Grammar Rule Induction for Spoken Dialogue Systems via Probabilistic Candidate Selection'. Together they form a unique fingerprint.

Cite this