Assessing the syntactic capabilities of transformer-based multilingual language models

Pérez-Mayos, Laura; Táboas García, Alba; Mille, Simon; Wanner, Leo

doi:http://dx.doi.org/10.18653/v1/2021.findings-acl.333

Assessing the syntactic capabilities of transformer-based multilingual language models

License

Citation

Pérez-Mayos L, Táboas García A, Mille S, Wanner L. Assessing the syntactic capabilities of transformer-based multilingual language models. In: Zong C, Xia F, Li Wenjie, Navigli R. Findings of the Association for Computational Linguistics (ACL-IJCNLP 2021); 2021 Aug 1-6; online. Stroudsburg: Association for Computational Linguistics; 2021. p. 3799-812. DOI: 10.18653/v1/2021.findings-acl.333

Abstract

Multilingual Transformer-based language models, usually pretrained on more than 100 languages, have been shown to achieve outstanding results in a wide range of crosslingual transfer tasks. However, it remains unknown whether the optimization for different languages conditions the capacity of the models to generalize over syntactic structures, and how languages with syntactic phenomena of different complexity are affected. In this work, we explore the syntactic generalization capabilities of the monolingual and multilingual versions of BERT and RoBERTa. More specifically, we evaluate the syntactic generalization potential of the models on English and Spanish tests, comparing the syntactic abilities of monolingual and multilingual models on the same language (English), and of multilingual models on two different languages (English and Spanish). For English, we use the available SyntaxGym test suite; for Spanish, we introduce SyntaxGymES, a novel ensemble of targeted syntactic tests in Spanish, designed to evaluate the syntactic generalization capabilities of language models through the SyntaxGym online platform.

Description

Comunicació presentada a Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, celebrat de l'1 al 6 d'agost de 2021 de manera virtual.