Improving Cross-lingual Transfer through Subtree-aware Word Reordering

Ofir Arviv, Dmitry Nikolaev, Taelin Karidi, Omri Abend

Abstract
Despite the impressive growth of the abilities of multilingual language models, such as XLM-R and mT5, it has been shown that they still face difficulties when tackling typologically-distant languages, particularly in the low-resource setting. One obstacle for effective cross-lingual transfer is variability in word-order patterns. It can be potentially mitigated via source- or target-side word reordering, and numerous approaches to reordering have been proposed. However, they rely on language-specific rules, work on the level of POS tags, or only target the main clause, leaving subordinate clauses intact. To address these limitations, we present a new powerful reordering method, defined in terms of Universal Dependencies, that is able to learn fine-grained word-order patterns conditioned on the syntactic context from a small amount of annotated data and can be applied at all levels of the syntactic tree. We conduct experiments on a diverse set of tasks and show that our method consistently outperforms strong baselines over different language pairs and model architectures. This performance advantage holds true in both zero-shot and few-shot scenarios.
Anthology ID:
2023.findings-emnlp.52
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
718–736
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.52
DOI:
10.18653/v1/2023.findings-emnlp.52
Bibkey:
Cite (ACL):
Ofir Arviv, Dmitry Nikolaev, Taelin Karidi, and Omri Abend. 2023. Improving Cross-lingual Transfer through Subtree-aware Word Reordering. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 718–736, Singapore. Association for Computational Linguistics.
Cite (Informal):
Improving Cross-lingual Transfer through Subtree-aware Word Reordering (Arviv et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-emnlp.52.pdf
PDF Search