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
2 LPC - Laboratoire de psychologie cognitive
3 LIF - Laboratoire d'informatique Fondamentale de Marseille

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.

Domains: Computer Science [cs]; Computation and Language [cs.CL]; Computer Science [cs]; Machine Learning [cs.LG]; Computer Science [cs]; Document and Text Processing; Computer Science [cs]; Signal and Image Processing

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. ⟨hal-01773220⟩