Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering
Arviv, Ofir, Nikolaev, Dmitry, Karidi, Taelin, Abend, Omri
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-20-2023
- Country:
- Oceania > Australia
- North America
- Dominican Republic (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- New Mexico > Santa Fe County
- Santa Fe (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- Washington > King County
- Canada > British Columbia
- Europe
- Czechia > Prague (0.04)
- Italy > Tuscany
- Florence (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Middle East > Cyprus
- Ukraine > Kyiv Oblast
- Kyiv (0.04)
- Germany > Baden-Württemberg
- Stuttgart Region > Stuttgart (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia
- Indonesia > Bali (0.04)
- Middle East
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Israel > Jerusalem District
- Jerusalem (0.04)
- UAE > Abu Dhabi Emirate
- Japan > Honshū
- Kansai
- Osaka Prefecture > Osaka (0.04)
- Kyoto Prefecture > Kyoto (0.04)
- Kansai
- China
- Genre:
- Research Report > New Finding (0.93)
- Technology: