Cross-lingual Transfer of Monolingual Models

Evangelia Gogoulou, Ariel Ekgren, Tim Isbister, Magnus Sahlgren


Abstract
Recent studies in cross-lingual learning using multilingual models have cast doubt on the previous hypothesis that shared vocabulary and joint pre-training are the keys to cross-lingual generalization. We introduce a method for transferring monolingual models to other languages through continuous pre-training and study the effects of such transfer from four different languages to English. Our experimental results on GLUE show that the transferred models outperform an English model trained from scratch, independently of the source language. After probing the model representations, we find that model knowledge from the source language enhances the learning of syntactic and semantic knowledge in English.
Anthology ID:
2022.lrec-1.100
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
948–955
Language:
URL:
https://aclanthology.org/2022.lrec-1.100
DOI:
Bibkey:
Cite (ACL):
Evangelia Gogoulou, Ariel Ekgren, Tim Isbister, and Magnus Sahlgren. 2022. Cross-lingual Transfer of Monolingual Models. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 948–955, Marseille, France. European Language Resources Association.
Cite (Informal):
Cross-lingual Transfer of Monolingual Models (Gogoulou et al., LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.100.pdf
Data
GLUE