Predicting the Success of Domain Adaptation in Text Similarity

Nick Pogrebnyakov, Shohreh Shaghaghian


Abstract
Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain adaptation. This paper models adaptation success and selection of the most suitable source domains among several candidates in text similarity. We use descriptive domain information and cross-domain similarity metrics as predictive features. While mostly positive, the results also point to some domains where adaptation success was difficult to predict.
Anthology ID:
2021.repl4nlp-1.21
Volume:
Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Anna Rogers, Iacer Calixto, Ivan Vulić, Naomi Saphra, Nora Kassner, Oana-Maria Camburu, Trapit Bansal, Vered Shwartz
Venue:
RepL4NLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
206–212
Language:
URL:
https://aclanthology.org/2021.repl4nlp-1.21
DOI:
10.18653/v1/2021.repl4nlp-1.21
Bibkey:
Cite (ACL):
Nick Pogrebnyakov and Shohreh Shaghaghian. 2021. Predicting the Success of Domain Adaptation in Text Similarity. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 206–212, Online. Association for Computational Linguistics.
Cite (Informal):
Predicting the Success of Domain Adaptation in Text Similarity (Pogrebnyakov & Shaghaghian, RepL4NLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.repl4nlp-1.21.pdf
Data
MRPCPAWS