Generating natural language descriptions using speaker-dependent information

Thiago Castro Ferreira, Ivandré Paraboni

Research output: Contribution to journalArticleScientificpeer-review

3 Citations (Scopus)

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.
Original languageEnglish
JournalNatural Language Engineering
DOIs
Publication statusPublished - 27 Feb 2017

Fingerprint Dive into the research topics of 'Generating natural language descriptions using speaker-dependent information'. Together they form a unique fingerprint.

  • Cite this