Modelling Pro-drop with the Rational Speech Acts Model

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

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


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 languageEnglish
Title of host publicationProceedings of the 11th International Conference on Natural Language Generation
Place of PublicationTilburg University, The Netherlands
PublisherAssociation for Computational Linguistics (ACL)
Number of pages6
ISBN (Electronic)978-1-948087-86-5
Publication statusPublished - 5 Nov 2018


Dive into the research topics of 'Modelling Pro-drop with the Rational Speech Acts Model'. Together they form a unique fingerprint.

Cite this