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.
BibTeX
@inproceedings{langedijk-etal-2022-meta,
title = "Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing",
author = "Langedijk, Anna and
Dankers, Verna and
Lippe, Phillip and
Bos, Sander and
Cardenas Guevara, Bryan and
Yannakoudakis, Helen and
Shutova, Ekaterina",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.582/",
doi = "10.18653/v1/2022.acl-long.582",
pages = "8503--8520"
}