Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2021

Abstract

Pre-trained multilingual language models, e.g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the state-of-the-art performance. However, such models suffer from a large performance gap between source and target languages, especially in the zero-shot setting, where the models are fine-tuned only on English but tested on other languages for the same task. We tackle this issue by incorporating language-agnostic information, specifically, universal syntax such as dependency relations and POS tags, into language models, based on the observation that universal syntax is transferable across different languages. Our approach, named COunterfactual SYntax (COSY), includes the design of SYntax-aware networks as well as a COunterfactual training method to implicitly force the networks to learn not only the semantics but also the syntax. To evaluate COSY, we conduct cross-lingual experiments on natural language inference and question answering using mBERT and XLM-R as network backbones. Our results show that COSY achieves the state-of-the-art performance for both tasks, without using auxiliary dataset.

Keywords

Computational linguistics, Natural language processing systems, Semantics

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

ACL-IJCNLP 2021: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics

First Page

577

Last Page

589

ISBN

9781954085527

Identifier

10.18653/v1/2021.acl-long.48

Publisher

Association for Computational Linguistics

City or Country

Online

Copyright Owner and License

Publisher

Additional URL

https://doi.org/10.18653/v1/2021.acl-long.48

Share

COinS