Modelling Pro-drop with the Rational Speech Acts Model

G. Chen; C.J. van Deemter; Chenghua Lin

doi:10.18653/v1/W18-6519

Modelling Pro-drop with the Rational Speech Acts Model

G. Chen, C.J. van Deemter, Chenghua Lin

Universtity of Aberdeen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We extend the classic Referring Expressions Generation task by considering zero pronouns in pro-drop languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model. By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically.

Original language	English
Title of host publication	Proceedings of the 11th International Conference on Natural Language Generation
Place of Publication	Tilburg University, The Netherlands
Publisher	Association for Computational Linguistics
Pages	57–66
Number of pages	6
ISBN (Electronic)	978-1-948087-86-5
DOIs	https://doi.org/10.18653/v1/W18-6519
Publication status	Published - 5 Nov 2018

Access to Document

10.18653/v1/W18-6519Licence: CC BY

simplenlgFinal published version, 423 KBLicence: CC BY

Cite this

@inproceedings{1534e651791d4826b629819f8f43ef4d,

title = "Modelling Pro-drop with the Rational Speech Acts Model",

abstract = "We extend the classic Referring Expressions Generation task by considering zero pronouns in pro-drop languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model. By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically.",

author = "G. Chen and {van Deemter}, C.J. and Chenghua Lin",

year = "2018",

month = nov,

day = "5",

doi = "10.18653/v1/W18-6519",

language = "English",

pages = "57–66",

booktitle = "Proceedings of the 11th International Conference on Natural Language Generation",

publisher = "Association for Computational Linguistics",

address = "United States",

}

Modelling Pro-drop with the Rational Speech Acts Model. / Chen, G.; van Deemter, C.J.; Lin, Chenghua.
Proceedings of the 11th International Conference on Natural Language Generation. Tilburg University, The Netherlands: Association for Computational Linguistics, 2018. p. 57–66.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Modelling Pro-drop with the Rational Speech Acts Model

AU - Chen, G.

AU - van Deemter, C.J.

AU - Lin, Chenghua

PY - 2018/11/5

Y1 - 2018/11/5

N2 - We extend the classic Referring Expressions Generation task by considering zero pronouns in pro-drop languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model. By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically.

AB - We extend the classic Referring Expressions Generation task by considering zero pronouns in pro-drop languages such as Chinese, modelling their use by means of the Bayesian Rational Speech Acts model. By assuming that highly salient referents are most likely to be referred to by zero pronouns (i.e., pro-drop is more likely for salient referents than the less salient ones), the model offers an attractive explanation of a phenomenon not previously addressed probabilistically.

U2 - 10.18653/v1/W18-6519

DO - 10.18653/v1/W18-6519

M3 - Conference contribution

SP - 57

EP - 66

BT - Proceedings of the 11th International Conference on Natural Language Generation

PB - Association for Computational Linguistics

CY - Tilburg University, The Netherlands

ER -

Modelling Pro-drop with the Rational Speech Acts Model

Abstract

Access to Document

Fingerprint

Cite this