Generating natural language descriptions using speaker-dependent information
Castro Ferreira,Thiago ; Paraboni,Ivandré
Castro Ferreira,Thiago
Paraboni,Ivandré
Abstract
This paper discusses the issue of human variation in natural language referring expression generation. We introduce a model of content selection that takes speaker-dependent information into account to produce descriptions that closely resemble those produced by each individual, as seen in a number of reference corpora. Results show that our speaker-dependent referring expression generation model outperforms alternatives that do not take human variation into account, or which do so less extensively, and suggest that the use of machine-learning methods may be an ideal approach to mimic complex referential behaviour.
Description
Date
2017-02-27
Journal Title
Journal ISSN
Volume Title
Publisher
Research Projects
Organizational Units
Journal Issue
Keywords
Citation
Castro Ferreira, T & Paraboni, I 2017, 'Generating natural language descriptions using speaker-dependent information', Natural Language Engineering. https://doi.org/10.1017/S1351324917000079
License
info:eu-repo/semantics/closedAccess
