Predicting the Success of Domain Adaptation in Text Similarity

Nicolai Pogrebnyakov*, Shohreh Shaghaghian

*Corresponding author af dette arbejde

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review


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.
TitelThe 6th Workshop on Representation Learning for NLP : Proceedings of the Workshop (REPL4NLP 2021)
RedaktørerAnna Rogers, Iacer Calixto, Iacer Calixto, Ivan Vulic, Naomi Saphra, Nora Kassner, Oana-Maria Camburu, Trapit Bansal, Vered Shwartz
Antal sider7
UdgivelsesstedStroudsburg, PA
ForlagAssociation for Computational Linguistics
ISBN (Trykt)9781954085725
ISBN (Elektronisk)9781954085725
StatusUdgivet - 2021

Bibliografisk 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).