Does typological blinding impede cross-lingual sharing?

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

Documents

Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features from databases such as the World Atlas of Language Structures (WALS) are a prime candidate for this, as such data exists even for very low-resource languages. However, previous work has only found minor benefits from using typological information. Our hypothesis is that a model trained in a cross-lingual setting will pick up on typological cues from the input data, thus overshadowing the utility of explicitly using such features. We verify this hypothesis by blinding a model to typological information, and investigate how cross-lingual sharing and performance is impacted. Our model is based on a cross-lingual architecture in which the latent weights governing the sharing between languages is learnt during training. We show that (i) preventing this model from exploiting typology severely reduces performance, while a control experiment reaffirms that (ii) encouraging sharing according to typology somewhat improves performance.

Original languageEnglish
Title of host publicationEACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics
Publication date2021
Pages480-486
ISBN (Electronic)9781954085022
DOIs
Publication statusPublished - 2021
Event16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 - Virtual, Online
Duration: 19 Apr 202123 Apr 2021

Conference

Conference16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021
ByVirtual, Online
Periode19/04/202123/04/2021
SponsorBabelscape, Bloomberg Engineering, Facebook AI, Grammarly, LegalForce

Bibliographical note

Publisher Copyright:
© 2021 Association for Computational Linguistics

ID: 283135291