Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling

Nuo Chen, Linjun Shou, Ming Gong, Jian Pei, Daxin Jiang


Abstract
Large-scale cross-lingual pre-trained language models (xPLMs) have shown effective in cross-lingual sequence labeling tasks (xSL), such as machine reading comprehension (xMRC) by transferring knowledge from a high-resource language to low-resource languages.Despite the great success, we draw an empirical observation that there is an training objective gap between pre-training and fine-tuning stages: e.g., mask language modeling objective requires local understanding of the masked token and the span-extraction objective requires understanding and reasoning of the global input passage/paragraph and question, leading to the discrepancy between pre-training and xMRC. In this paper, we first design a pre-training task tailored for xSL named Cross-lingual Language Informative Span Masking (CLISM) to eliminate the objective gap in a self-supervised manner. Second, we present ContrAstive-Consistency Regularization (CACR), which utilizes contrastive learning to encourage the consistency between representations of input parallel sequences via unsupervised cross-lingual instance-wise training signals during pre-training. By these means, our methods not only bridge the gap between pretrain-finetune, but also enhance PLMs to better capture the alignment between different languages. Extensive experiments prove that our method achieves clearly superior results on multiple xSL benchmarks with limited pre-training data. Our methods also surpass the previous state-of-the-art methods by a large margin in few-shot data setting, where only a few hundred training examples are available.
Anthology ID:
2022.naacl-main.139
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1909–1923
Language:
URL:
https://aclanthology.org/2022.naacl-main.139
DOI:
10.18653/v1/2022.naacl-main.139
Bibkey:
Cite (ACL):
Nuo Chen, Linjun Shou, Ming Gong, Jian Pei, and Daxin Jiang. 2022. Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1909–1923, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling (Chen et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.139.pdf
Data
MLQAWikiAnnXQuAD