Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding

Xuxin Cheng, Zhihong Zhu, Bang Yang, Xianwei Zhuang, Hongxiang Li, Yuexian Zou


Abstract
Owing to the scarcity of labeled training data, Spoken Language Understanding (SLU) is still a challenging task in low-resource languages. Therefore, zero-shot cross-lingual SLU attracts more and more attention. Contrastive learning is widely applied to explicitly align representations of similar sentences across different languages. However, the vanilla contrastive learning method may face two problems in zero-shot cross-lingual SLU: (1) the consistency between different languages is neglected; (2) each utterance has two different kinds of SLU labels, i.e. slot and intent, the utterances with one different label are also pushed away without any discrimination, which limits the performance. In this paper, we propose Cyclical Contrastive Learning based on Geodesic (CCLG), which introduces cyclical contrastive learning to achieve the consistency between different languages and leverages geodesic to measure the similarity to construct the positive pairs and negative pairs. Experimental results demonstrate that our proposed framework achieves the new state-of-the-art performance on MultiATIS++ and MTOP datasets, and the model analysis further verifies that CCLG can effectively transfer knowledge between different languages.
Anthology ID:
2024.findings-acl.106
Original:
2024.findings-acl.106v1
Version 2:
2024.findings-acl.106v2
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1806–1816
Language:
URL:
https://aclanthology.org/2024.findings-acl.106
DOI:
10.18653/v1/2024.findings-acl.106
Bibkey:
Cite (ACL):
Xuxin Cheng, Zhihong Zhu, Bang Yang, Xianwei Zhuang, Hongxiang Li, and Yuexian Zou. 2024. Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding. In Findings of the Association for Computational Linguistics: ACL 2024, pages 1806–1816, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding (Cheng et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.106.pdf