Modeling the interpretation of discourse connectives by Bayesian pragmatics

Frances Yung; Kevin Duh; Taku Komura; Yuji Matsumoto

doi:10.18653/v1/P16-2086

Modeling the interpretation of discourse connectives by Bayesian pragmatics

Frances Yung, Kevin Duh, Taku Komura, Yuji Matsumoto

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

We propose a framework to model human comprehension of discourse connectives. Following the Bayesian pragmatic paradigm, we advocate that discourse connectives are interpreted based on a simulation of the production process by the speaker, who, in turn, considers the ease of interpretation for the listener when choosing connectives. Evaluation against the sense annotation of the Penn Discourse Treebank confirms the superiority of the model over literal comprehension. A further experiment demonstrates that the proposed model also improves automatic discourse parsing.

Original language	English
Title of host publication	The 54th Annual Meeting of the Association for Computational Linguistics
Place of Publication	Berlin, Germany
Publisher	Association for Computational Linguistics (ACL)
Pages	531-536
Number of pages	6
ISBN (Electronic)	9781510827592
ISBN (Print)	978-1-945626-00-5
DOIs	https://doi.org/10.18653/v1/P16-2086
Publication status	Published - 12 Aug 2016
Event	54th Annual Meeting of the Association for Computational Linguistics - Berlin, Germany Duration: 7 Aug 2016 → 12 Aug 2016 https://mirror.aclweb.org/acl2016/

Conference

Conference	54th Annual Meeting of the Association for Computational Linguistics
Abbreviated title	ACL 2016
Country/Territory	Germany
City	Berlin
Period	7/08/16 → 12/08/16
Internet address	https://mirror.aclweb.org/acl2016/

Access to Document

10.18653/v1/P16-2086Licence: Creative Commons: Attribution (CC-BY)

camera_ready1-1Accepted author manuscript, 211 KB
P16-2086Final published version, 178 KBLicence: Creative Commons: Attribution (CC-BY)

http://anthology.aclweb.org/P16-2086Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{13e953e7e25d41369f95346271bd47fa,

title = "Modeling the interpretation of discourse connectives by Bayesian pragmatics",

abstract = "We propose a framework to model human comprehension of discourse connectives. Following the Bayesian pragmatic paradigm, we advocate that discourse connectives are interpreted based on a simulation of the production process by the speaker, who, in turn, considers the ease of interpretation for the listener when choosing connectives. Evaluation against the sense annotation of the Penn Discourse Treebank confirms the superiority of the model over literal comprehension. A further experiment demonstrates that the proposed model also improves automatic discourse parsing.",

author = "Frances Yung and Kevin Duh and Taku Komura and Yuji Matsumoto",

year = "2016",

month = aug,

day = "12",

doi = "10.18653/v1/P16-2086",

language = "English",

isbn = "978-1-945626-00-5",

pages = "531--536",

booktitle = "The 54th Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

note = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 ; Conference date: 07-08-2016 Through 12-08-2016",

url = "https://mirror.aclweb.org/acl2016/",

}

Yung, F, Duh, K, Komura, T & Matsumoto, Y 2016, Modeling the interpretation of discourse connectives by Bayesian pragmatics. in The 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (ACL), Berlin, Germany, pp. 531-536, 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany, 7/08/16. https://doi.org/10.18653/v1/P16-2086

Modeling the interpretation of discourse connectives by Bayesian pragmatics. / Yung, Frances; Duh, Kevin; Komura, Taku et al.
The 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany: Association for Computational Linguistics (ACL), 2016. p. 531-536.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Modeling the interpretation of discourse connectives by Bayesian pragmatics

AU - Yung, Frances

AU - Duh, Kevin

AU - Komura, Taku

AU - Matsumoto, Yuji

PY - 2016/8/12

Y1 - 2016/8/12

N2 - We propose a framework to model human comprehension of discourse connectives. Following the Bayesian pragmatic paradigm, we advocate that discourse connectives are interpreted based on a simulation of the production process by the speaker, who, in turn, considers the ease of interpretation for the listener when choosing connectives. Evaluation against the sense annotation of the Penn Discourse Treebank confirms the superiority of the model over literal comprehension. A further experiment demonstrates that the proposed model also improves automatic discourse parsing.

AB - We propose a framework to model human comprehension of discourse connectives. Following the Bayesian pragmatic paradigm, we advocate that discourse connectives are interpreted based on a simulation of the production process by the speaker, who, in turn, considers the ease of interpretation for the listener when choosing connectives. Evaluation against the sense annotation of the Penn Discourse Treebank confirms the superiority of the model over literal comprehension. A further experiment demonstrates that the proposed model also improves automatic discourse parsing.

U2 - 10.18653/v1/P16-2086

DO - 10.18653/v1/P16-2086

M3 - Conference contribution

AN - SCOPUS:85016614287

SN - 978-1-945626-00-5

SP - 531

EP - 536

BT - The 54th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

CY - Berlin, Germany

T2 - 54th Annual Meeting of the Association for Computational Linguistics

Y2 - 7 August 2016 through 12 August 2016

ER -

Modeling the interpretation of discourse connectives by Bayesian pragmatics

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this