Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/90389
PIRA download icon_1.1View/Download Full Text
Title: Are word embeddings really a bad fit for the estimation of thematic fit?
Authors: Chersoni, E 
Pannitto, L
Santus, E
Lenci, A
Huang, CR 
Issue Date: 2020
Source: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), Marseille, France, May 2020, p. 5708-5713
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.
Keywords: Semantics
Cognitive methods
Statistical and machine learning methods
Rights: © European Language Resources Association (ELRA), licensed under CC-BY-NC (https://creativecommons.org/licenses/by/4.0/).
The following publication Chersoni, E., Pannitto, L., Santus, E., Lenci, A., & Huang, C. R. (2020, May). Are Word Embeddings Really a Bad Fit for the Estimation of Thematic Fit?. In Proceedings of The 12th Language Resources and Evaluation Conference (pp. 5708-5713) is available at https://www.aclweb.org/anthology/2020.lrec-1.700
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
2020.lrec-1.700.pdf711.42 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

52
Citations as of May 22, 2022

Downloads

1
Citations as of May 22, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.