A Computational Model of Human Preferences for Pronoun Resolution - Université Paris Cité Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

A Computational Model of Human Preferences for Pronoun Resolution

Résumé

We present a cognitive computational model of pronoun resolution that reproduces the human interpretation preferences of the Subject Assignment Strategy and the Parallel Function Strategy. Our model relies on a probabilistic pronoun resolution system trained on corpus data. Factors influencing pronoun resolution are represented as features weighted by their relative importance. The importance the model gives to the preferences is in line with psycholinguistic studies. We demonstrate the cognitive plausibility of the model by running it on experimental items and simulating antecedent choice and reading times of human participants. Our model can be used as a new means to study pronoun resolution, because it captures the interaction of preferences.

Domaines

Linguistique
Fichier principal
Vignette du fichier
SRW2017.pdf (2.02 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

halshs-01955078 , version 1 (19-09-2022)

Identifiants

  • HAL Id : halshs-01955078 , version 1

Citer

Olga Seminck, Pascal Amsili. A Computational Model of Human Preferences for Pronoun Resolution. The Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics 2017, Apr 2017, Valencia, Spain. ⟨halshs-01955078⟩
75 Consultations
10 Téléchargements

Partager

Gmail Facebook X LinkedIn More