Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding

Shining Liang, Linjun Shou, Jian Pei, Ming Gong, Wanli Zuo, Xianglin Zuo, Daxin Jiang


Abstract
Despite the great success of spoken language understanding (SLU) in high-resource languages, it remains challenging in low-resource languages mainly due to the lack of labeled training data. The recent multilingual code-switching approach achieves better alignments of model representations across languages by constructing a mixed-language context in zero-shot cross-lingual SLU. However, current code-switching methods are limited to implicit alignment and disregard the inherent semantic structure in SLU, i.e., the hierarchical inclusion of utterances, slots and words. In this paper, we propose to model the utterance-slot-word structure by a multi-level contrastive learning framework at the utterance, slot and word levels to facilitate explicit alignment. Novel code-switching schemes are introduced to generate hard negative examples for our contrastive learning framework. Furthermore, we develop a label-aware joint model leveraging label semantics to enhance the implicit alignment and feed to contrastive learning. Our experimental results show that our proposed methods significantly improve the performance compared with the strong baselines on two zero-shot cross-lingual SLU benchmark datasets.
Anthology ID:
2022.emnlp-main.673
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9903–9918
Language:
URL:
https://aclanthology.org/2022.emnlp-main.673
DOI:
10.18653/v1/2022.emnlp-main.673
Bibkey:
Cite (ACL):
Shining Liang, Linjun Shou, Jian Pei, Ming Gong, Wanli Zuo, Xianglin Zuo, and Daxin Jiang. 2022. Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9903–9918, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding (Liang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.673.pdf