Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/90389
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 | Size | Format | |
---|---|---|---|---|
2020.lrec-1.700.pdf | 711.42 kB | Adobe PDF | View/Open |
Page views
66
Last Week
0
0
Last month
Citations as of May 28, 2023
Downloads
5
Citations as of May 28, 2023

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