English

Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering

Computation and Language 2023-10-23 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.2310.13583,
  title  = {Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering},
  author = {Ofir Arviv and Dmitry Nikolaev and Taelin Karidi and Omri Abend},
  journal= {arXiv preprint arXiv:2310.13583},
  year   = {2023}
}

Comments

Accepted to EMNLP Findings 2023

R2 v1 2026-06-28T12:56:59.130Z