Predicting the Success of Domain Adaptation in Text Similarity

Nicolai Pogrebnyakov*, Shohreh Shaghaghian

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

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.
Original languageEnglish
Title of host publicationThe 6th Workshop on Representation Learning for NLP : Proceedings of the Workshop (REPL4NLP 2021)
Number of pages7
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics
Publication date2021
Pages206-212
ISBN (Print)9781954085725
Publication statusPublished - 2021

Bibliographical note

Part of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021).

Cite this