NAACL 2022long40 citations
BAD-X: Bilingual Adapters Improve Zero-Shot Cross-Lingual Transfer
Marinela Parović, Goran Glavaš, Ivan Vulić, Anna Korhonen
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.
BibTeX
@inproceedings{parovic-etal-2022-bad,
title = "{BAD}-{X}: Bilingual Adapters Improve Zero-Shot Cross-Lingual Transfer",
author = "Parovi{\'c}, Marinela and
Glava{\v{s}}, Goran and
Vuli{\'c}, Ivan and
Korhonen, Anna",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.130/",
doi = "10.18653/v1/2022.naacl-main.130",
pages = "1791--1799"
}