TY - JOUR
T1 - Generating natural language descriptions using speaker-dependent information
AU - Castro Ferreira, Thiago
AU - Paraboni, Ivandré
PY - 2017/2/27
Y1 - 2017/2/27
N2 - 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.
AB - 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.
U2 - 10.1017/S1351324917000079
DO - 10.1017/S1351324917000079
M3 - Article
SN - 1351-3249
JO - Natural Language Engineering
JF - Natural Language Engineering
ER -