Modeling the Usage of Discourse Connectives as Rational Speech Acts

Frances Yung, Kevin Duh, Taku Komura, Yuji Matsumoto

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

Abstract / Description of output

Discourse relations can either be implicit or explicitly expressed by markers, such as ’therefore’ and ’but’. How a speaker makes this choice is a question that is not well understood. We propose a psycholinguistic model that predicts whether a speaker will produce an explicit marker given the discourse relation s/he wishes to express. Based on the framework of the Rational Speech Acts model, we quantify the utility of producing a marker based on the information-theoretic measure of surprisal, the cost of production, and a bias to maintain uniform information density throughout the utterance. Experiments based on the Penn Discourse Treebank show that our approach outperforms state of-the-art approaches, while giving an explanatory account of the speaker’s choice.
Original languageEnglish
Title of host publicationProceedings of the 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL)
Place of PublicationBerlin, Germany
PublisherAssociation for Computational Linguistics (ACL)
Pages302–313
Number of pages12
ISBN (Electronic)978-1-945626-19-7
DOIs
Publication statusPublished - 12 Aug 2016
Event20th SIGNLL Conference on Computational Natural Language Learning - Berlin, Germany
Duration: 11 Aug 201612 Aug 2016
http://www.conll.org/2016

Conference

Conference20th SIGNLL Conference on Computational Natural Language Learning
Abbreviated titleCoNLL
Country/TerritoryGermany
CityBerlin
Period11/08/1612/08/16
Internet address

Fingerprint

Dive into the research topics of 'Modeling the Usage of Discourse Connectives as Rational Speech Acts'. Together they form a unique fingerprint.

Cite this