XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
Zewen Chi, Shaohan Huang, Li Dong, Shuming Ma, Bo Zheng, Saksham Singhal, Payal Bajaj, Xia Song, Xian-Ling Mao, Heyan Huang, Furu Wei
Abstract
In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides, we pretrain the model, named as XLM-E, on both multilingual and parallel corpora. Our model outperforms the baseline models on various cross-lingual understanding tasks with much less computation cost. Moreover, analysis shows that XLM-E tends to obtain better cross-lingual transferability.- Anthology ID:
- 2022.acl-long.427
- 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:
- 6170–6182
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.427
- DOI:
- 10.18653/v1/2022.acl-long.427
- Cite (ACL):
- Zewen Chi, Shaohan Huang, Li Dong, Shuming Ma, Bo Zheng, Saksham Singhal, Payal Bajaj, Xia Song, Xian-Ling Mao, Heyan Huang, and Furu Wei. 2022. XLM-E: Cross-lingual Language Model Pre-training via ELECTRA. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6170–6182, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- XLM-E: Cross-lingual Language Model Pre-training via ELECTRA (Chi et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2022.acl-long.427.pdf
- Code
- microsoft/unilm + additional community code
- Data
- CC100, MLQA, PAWS-X, TyDi QA, XNLI, XQuAD, XTREME