Enhancing Code-Switching for Cross-lingual SLU: A Unified View of Semantic and Grammatical Coherence

Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen, Yuexian Zou


Abstract
Despite the success of spoken language understanding (SLU) in high-resource languages, achieving similar performance in low-resource settings, such as zero-shot scenarios, remains challenging due to limited labeled training data. To improve zero-shot cross-lingual SLU, recent studies have explored code-switched sentences containing tokens from multiple languages. However, vanilla code-switched sentences often lack semantic and grammatical coherence. We ascribe this lack to two issues: (1) randomly replacing code-switched tokens with equal probability and (2) disregarding token-level dependency within each language. To tackle these issues, in this paper, we propose a novel method termed SoGo, for zero-shot cross-lingual SLU. First, we use a saliency-based substitution approach to extract keywords as substitution options. Then, we introduce a novel token-level alignment strategy that considers the similarity between the context and the code-switched tokens, ensuring grammatical coherence in code-switched sentences. Extensive experiments and analyses demonstrate the superior performance of SoGo across nine languages on MultiATIS++.
Anthology ID:
2023.emnlp-main.486
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7849–7856
Language:
URL:
https://aclanthology.org/2023.emnlp-main.486
DOI:
10.18653/v1/2023.emnlp-main.486
Bibkey:
Cite (ACL):
Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen, and Yuexian Zou. 2023. Enhancing Code-Switching for Cross-lingual SLU: A Unified View of Semantic and Grammatical Coherence. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7849–7856, Singapore. Association for Computational Linguistics.
Cite (Informal):
Enhancing Code-Switching for Cross-lingual SLU: A Unified View of Semantic and Grammatical Coherence (Zhu et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.486.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.486.mp4