Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos, Bryan Cardenas Guevara, Helen Yannakoudakis, Ekaterina Shutova


Abstract
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of cross-lingual dependency parsing. We train our model on a diverse set of languages to learn a parameter initialization that can adapt quickly to new languages. We find that meta-learning with pre-training can significantly improve upon the performance of language transfer and standard supervised learning baselines for a variety of unseen, typologically diverse, and low-resource languages, in a few-shot learning setup.
Anthology ID:
2022.acl-long.582
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8503–8520
Language:
URL:
https://aclanthology.org/2022.acl-long.582
DOI:
10.18653/v1/2022.acl-long.582
Bibkey:
Cite (ACL):
Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos, Bryan Cardenas Guevara, Helen Yannakoudakis, and Ekaterina Shutova. 2022. Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8503–8520, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing (Langedijk et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.582.pdf
Software:
 2022.acl-long.582.software.zip
Code
 annaproxy/udify-metalearning