Why is sentence similarity benchmark not predictive of application-oriented task performance?

Kaori Abe, Sho Yokoi, Tomoyuki Kajiwara, Kentaro Inui


Anthology ID:
2022.eval4nlp-1.8
Volume:
Proceedings of the 3rd Workshop on Evaluation and Comparison of NLP Systems
Month:
November
Year:
2022
Address:
Online
Editors:
Daniel Deutsch, Can Udomcharoenchaikit, Juri Opitz, Yang Gao, Marina Fomicheva, Steffen Eger
Venue:
Eval4NLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
70–87
Language:
URL:
https://aclanthology.org/2022.eval4nlp-1.8
DOI:
10.18653/v1/2022.eval4nlp-1.8
Bibkey:
Cite (ACL):
Kaori Abe, Sho Yokoi, Tomoyuki Kajiwara, and Kentaro Inui. 2022. Why is sentence similarity benchmark not predictive of application-oriented task performance?. In Proceedings of the 3rd Workshop on Evaluation and Comparison of NLP Systems, pages 70–87, Online. Association for Computational Linguistics.
Cite (Informal):
Why is sentence similarity benchmark not predictive of application-oriented task performance? (Abe et al., Eval4NLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.eval4nlp-1.8.pdf
Supplementary material:
 2022.eval4nlp-1.8.SupplementaryMaterial.zip