TY - GEN
T1 - Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering
AU - Arviv, Ofir
AU - Nikolaev, Dmitry
AU - Karidi, Taelin
AU - Abend, Omri
N1 - Publisher Copyright: © 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85183311093&partnerID=8YFLogxK
U2 - 10.18653/v1/2023.findings-emnlp.52
DO - 10.18653/v1/2023.findings-emnlp.52
M3 - منشور من مؤتمر
T3 - Findings of the Association for Computational Linguistics: EMNLP 2023
SP - 718
EP - 736
BT - Findings of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 2023 Findings of the Association for Computational Linguistics: EMNLP 2023
Y2 - 6 December 2023 through 10 December 2023
ER -