Are Word Embeddings Really a Bad Fit for the Estimation of Thematic Fit?

Emmanuele Chersoni, Ludovica Pannitto, Enrico Santus, A. Lenci, Chu-ren Huang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

While neural embeddings represent a popular choice for word representation in a wide variety of NLP tasks, their usage for thematic fit modeling has been limited, as they have been reported to lag behind syntax-based count models. In this paper, we propose a complete evaluation of count models and word embeddings on thematic fit estimation, by taking into account a larger number of parameters
and verb roles and introducing also dependency-based embeddings in the comparison. Our results show a complex scenario, where a determinant factor for the performance seems to be the availability to the model of reliable syntactic information for building the distributional representations of the roles.
Original languageEnglish
Title of host publicationProceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)
Pages5708
Number of pages5713
Publication statusPublished - May 2020

Cite this