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
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.naacl-main.139.pdf
- Data
- MLQA, WikiAnn, XQuAD