Nothing Special   »   [go: up one dir, main page]

Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages

Zheng Li, Mukul Kumar, William Headden, Bing Yin, Ying Wei, Yu Zhang, Qiang Yang


Abstract
Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks. However, mPLM-based methods usually involve two problems: (1) simply fine-tuning may not adapt general-purpose multilingual representations to be task-aware on low-resource languages; (2) ignore how cross-lingual adaptation happens for downstream tasks. To address the issues, we propose a meta graph learning (MGL) method. Unlike prior works that transfer from scratch, MGL can learn to cross-lingual transfer by extracting meta-knowledge from historical CLT experiences (tasks), making mPLM insensitive to low-resource languages. Besides, for each CLT task, MGL formulates its transfer process as information propagation over a dynamic graph, where the geometric structure can automatically capture intrinsic language relationships to explicitly guide cross-lingual transfer. Empirically, extensive experiments on both public and real-world datasets demonstrate the effectiveness of the MGL method.
Anthology ID:
2020.emnlp-main.179
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2290–2301
Language:
URL:
https://aclanthology.org/2020.emnlp-main.179
DOI:
10.18653/v1/2020.emnlp-main.179
Bibkey:
Cite (ACL):
Zheng Li, Mukul Kumar, William Headden, Bing Yin, Ying Wei, Yu Zhang, and Qiang Yang. 2020. Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2290–2301, Online. Association for Computational Linguistics.
Cite (Informal):
Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages (Li et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.179.pdf
Optional supplementary material:
 2020.emnlp-main.179.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38938702