MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning

Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah


Abstract
The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without large-scale monolingual corpora for pre-training or sufficient annotated data for fine-tuning, transfer learning remains an understudied and challenging task. Moreover, recent work shows that multilingual representations are surprisingly disjoint across languages, bringing additional challenges for transfer onto extremely low-resource languages. In this paper, we propose MetaXL, a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer. Extensive experiments on real-world low-resource languages – without access to large-scale monolingual corpora or large amounts of labeled data – for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach. Code for MetaXL is publicly available at github.com/microsoft/MetaXL.
Anthology ID:
2021.naacl-main.42
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
499–511
Language:
URL:
https://aclanthology.org/2021.naacl-main.42
DOI:
10.18653/v1/2021.naacl-main.42
Bibkey:
Cite (ACL):
Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, and Ahmed Hassan Awadallah. 2021. MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 499–511, Online. Association for Computational Linguistics.
Cite (Informal):
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning (Xia et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.42.pdf
Code
 microsoft/MetaXL