BAD-X: Bilingual Adapters Improve Zero-Shot Cross-Lingual Transfer

Anonymous

Paper Link: https://openreview.net/forum?id=XoX-pZFp_Zl

Paper Type: Short paper (up to four pages of content + unlimited references and appendices)

Abstract: Adapter modules enable modular and efficient zero-shot cross-lingual transfer, where current state-of-the-art adapter-based approaches learn specialized language adapters (LAs) for individual languages. In this work, we show that it is more effective to learn bilingual language pair adapters (BAs) when the goal is to optimize performance for a particular source-target transfer direction. Our novel BAD-X adapter framework trades off some modularity of dedicated LAs for improved transfer performance: we demonstrate consistent gains in three standard downstream tasks, and for the majority of evaluated low-resource languages.

Presentation Mode: This paper will be presented virtually

Virtual Presentation Timezone: UTC+1

Copyright Consent Signature (type Name Or NA If Not Transferrable): Marinela Parovic

Copyright Consent Name And Address: University of Cambridge, The Old Schools, Trinity Lane, Cambridge CB2 1TN, United Kingdom