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.
Email your librarian or administrator to recommend adding this journal to your organisation's collection.
* Views captured on Cambridge Core between 27th February 2017 - 22nd August 2017. This data will be updated every 24 hours.