Busca avançada
Ano de início
Entree


Referring Expression Generation in time-constrained communication

Autor(es):
Mostrar menos -
Mariotti, Andre Costa ; Paraboni, Ivandre ; Declerck, T ; Calzolari, N ; Choukri, K ; Cieri, C ; Hasida, K ; Isahara, H ; Maegaard, B ; Mariani, J ; Moreno, A ; Odijk, J ; Piperidis, S ; Tokunaga, T ; Goggi, S ; Mazo, H
Número total de Autores: 16
Tipo de documento: Artigo Científico
Fonte: PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018); v. N/A, p. 6-pg., 2018-01-01.
Resumo

In game-like applications and many others, an underlying Natural Language Generation system may have to express urgency or other dynamic aspects of a fast-evolving situation as text, which may be considerably different from text produced under so-called 'normal' circumstances (e.g., without time constrains). As a means to shed light on possible differences of this kind, this paper addresses the computational generation of natural language text in time-constrained communication by presenting two experiments that use the attribute selection task of definite descriptions (or Referring Expression Generation - REG) as a working example. In the first experiment, we describe a psycholinguistic study in which human participants are engaged in a time-constrained reference production task. This results in a corpus of time-constrained descriptions to be compared with 'normal' descriptions available from an existing (i.e., with no time constraint) REG corpus. In the second experiment, we discuss how a REG algorithm may be customised so as to produce time-constrained descriptions that resemble those produced by human speakers in similar situations. The proposed algorithm is then evaluated against the time-constrained descriptions produced by the human subjects in the first experiment, and it is shown to outperform standard approaches to REG in these conditions. (AU)

Processo FAPESP: 16/14223-0 - Tratamento Computacional da Personalidade Humana para Aplicações de Processamento de Língua Natural
Beneficiário:Ivandre Paraboni
Modalidade de apoio: Auxílio à Pesquisa - Regular