Evaluation of word embeddings against cognitive processes: primed reaction times in lexical decision and naming tasks

Jeremy Auguste 1 Arnaud Rey 2 Benoit Favre 1, 3
1 TALEP - Traitement Automatique du Langage Ecrit et Parlé
LIS - Laboratoire d'Informatique et Systèmes
2 LPC - Laboratoire de psychologie cognitive
3 LIF - Laboratoire d'informatique Fondamentale de Marseille
Abstract : This work presents a framework for word similarity evaluation grounded on cogni-tive sciences experimental data. Word pair similarities are compared to reaction times of subjects in large scale lexical decision and naming tasks under semantic priming. Results show that GloVe embeddings lead to significantly higher correlation with experimental measurements than other controlled and off-the-shelf embeddings, and that the choice of a training corpus is less important than that of the algorithm. Comparison of rankings with other datasets shows that the cognitive phenomenon covers more aspects than simply word related-ness or similarity.
Type de document :
Communication dans un congrès
Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP, 2017, Copenhagen, Denmark. pp.21 - 26, 2017
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger
https://hal-amu.archives-ouvertes.fr/hal-01773220
Contributeur : Benoit Favre <>
Soumis le : mardi 24 avril 2018 - 13:32:59
Dernière modification le : jeudi 14 juin 2018 - 01:02:23
Document(s) archivé(s) le : mardi 18 septembre 2018 - 17:42:29

Fichier

favre_repeval2017.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01773220, version 1

Collections

UNIV-AMU | LIF | LPC | LIS-LAB | UNIV-TLN | EC-MARSEILLE

Citation

Jeremy Auguste, Arnaud Rey, Benoit Favre. Evaluation of word embeddings against cognitive processes: primed reaction times in lexical decision and naming tasks. Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP, 2017, Copenhagen, Denmark. pp.21 - 26, 2017. 〈hal-01773220〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

90

Téléchargements de fichiers

51

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD