Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model

Tsung-Yuan Hsu, Chi-Liang Liu, Hung-yi Lee


Abstract
Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading comprehension tasks with language representation model pre-trained on multi-lingual corpus. The experimental results show that with pre-trained language representation zero-shot learning is feasible, and translating the source data into the target language is not necessary and even degrades the performance. We further explore what does the model learn in zero-shot setting.
Anthology ID:
D19-1607
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5933–5940
Language:
URL:
https://aclanthology.org/D19-1607
DOI:
10.18653/v1/D19-1607
Bibkey:
Cite (ACL):
Tsung-Yuan Hsu, Chi-Liang Liu, and Hung-yi Lee. 2019. Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5933–5940, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model (Hsu et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1607.pdf
Attachment:
 D19-1607.Attachment.pdf
Data
DRCDSQuAD