Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/90389
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Chinese and Bilingual Studies | en_US |
| dc.creator | Chersoni, E | en_US |
| dc.creator | Pannitto, L | en_US |
| dc.creator | Santus, E | en_US |
| dc.creator | Lenci, A | en_US |
| dc.creator | Huang, CR | en_US |
| dc.date.accessioned | 2021-06-28T07:25:46Z | - |
| dc.date.available | 2021-06-28T07:25:46Z | - |
| dc.identifier.uri | http://hdl.handle.net/10397/90389 | - |
| dc.language.iso | en | en_US |
| dc.rights | © European Language Resources Association (ELRA), licensed under CC-BY-NC (https://creativecommons.org/licenses/by/4.0/). | en_US |
| dc.rights | 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 | en_US |
| dc.subject | Semantics | en_US |
| dc.subject | Cognitive methods | en_US |
| dc.subject | Statistical and machine learning methods | en_US |
| dc.title | Are word embeddings really a bad fit for the estimation of thematic fit? | en_US |
| dc.type | Conference Paper | en_US |
| dc.identifier.spage | 5708 | en_US |
| dc.identifier.epage | 5713 | en_US |
| dcterms.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. | en_US |
| dcterms.accessRights | open access | en_US |
| dcterms.bibliographicCitation | Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), Marseille, France, May 2020, p. 5708-5713 | en_US |
| dcterms.issued | 2020 | - |
| dc.relation.ispartofbook | Proceedings of the 12th Language Resources and Evaluation Conference | en_US |
| dc.relation.conference | Language Resources and Evaluation Conference | en_US |
| dc.description.validate | 202106 bcvc | en_US |
| dc.description.oa | Version of Record | en_US |
| dc.identifier.FolderNumber | a0670-n19 | - |
| dc.description.pubStatus | Published | en_US |
| 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 |
Access
View full-text via PolyU eLinks 
Page views
53
Citations as of Jul 3, 2022
Downloads
1
Citations as of Jul 3, 2022
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.