Does Typological Blinding Impede Cross-Lingual Sharing?

Johannes Bjerva, Isabelle Augenstein

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

12 Citations (Scopus)

Abstract

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 publicationProceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
EditorsPaola Merlo, Jorg Tiedemann, Reut Tsarfaty
PublisherAssociation for Computational Linguistics
Publication date21 Apr 2021
Pages480-486
DOIs
Publication statusPublished - 21 Apr 2021
EventConference of the European Chapter
of the Association for Computational Linguistics
-
Duration: 21 Apr 202123 Apr 2021
Conference number: 16
https://2021.eacl.org/

Conference

ConferenceConference of the European Chapter
of the Association for Computational Linguistics
Number16
Period21/04/202123/04/2021
Internet address

Keywords

  • Natural Language Processing
  • Machine Learning
  • Computational Linguistics

Fingerprint

Dive into the research topics of 'Does Typological Blinding Impede Cross-Lingual Sharing?'. Together they form a unique fingerprint.

Cite this