File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.18653/v1/K16-1030
- Scopus: eid_2-s2.0-85072750976
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Modeling the usage of discourse connectives as rational speech acts
Title | Modeling the usage of discourse connectives as rational speech acts |
---|---|
Authors | |
Issue Date | 2016 |
Publisher | Association for Computational Linguistics. |
Citation | 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL 2016), Berlin, Germany, 7-12 August 2016. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, 2016, p. 302-313 How to Cite? |
Abstract | © 2016 Association for Computational Linguistics. 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. |
Persistent Identifier | http://hdl.handle.net/10722/288959 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yung, Frances | - |
dc.contributor.author | Duh, Kevin | - |
dc.contributor.author | Komura, Taku | - |
dc.contributor.author | Matsumoto, Yuji | - |
dc.date.accessioned | 2020-10-12T08:06:19Z | - |
dc.date.available | 2020-10-12T08:06:19Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL 2016), Berlin, Germany, 7-12 August 2016. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, 2016, p. 302-313 | - |
dc.identifier.uri | http://hdl.handle.net/10722/288959 | - |
dc.description.abstract | © 2016 Association for Computational Linguistics. 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. | - |
dc.language | eng | - |
dc.publisher | Association for Computational Linguistics. | - |
dc.relation.ispartof | Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.title | Modeling the usage of discourse connectives as rational speech acts | - |
dc.type | Conference_Paper | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.18653/v1/K16-1030 | - |
dc.identifier.scopus | eid_2-s2.0-85072750976 | - |
dc.identifier.spage | 302 | - |
dc.identifier.epage | 313 | - |