Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning

Xiang Yu, Zhang Ting, Di Hui, Huang Hui, Li Chunyou, Ouchi Kazushige, Chen Yufeng, Xu Jinan


Abstract
“Recent works in dialogue state tracking (DST) focus on a handful of languages, as collectinglarge-scale manually annotated data in different languages is expensive. Existing models addressthis issue by code-switched data augmentation or intermediate fine-tuning of multilingual pre-trained models. However, these models can only perform implicit alignment across languages. In this paper, we propose a novel model named Contrastive Learning for Cross-Lingual DST(CLCL-DST) to enhance zero-shot cross-lingual adaptation. Specifically, we use a self-builtbilingual dictionary for lexical substitution to construct multilingual views of the same utterance. Then our approach leverages fine-grained contrastive learning to encourage representations ofspecific slot tokens in different views to be more similar than negative example pairs. By thismeans, CLCL-DST aligns similar words across languages into a more refined language-invariantspace. In addition, CLCL-DST uses a significance-based keyword extraction approach to selecttask-related words to build the bilingual dictionary for better cross-lingual positive examples. Experiment results on Multilingual WoZ 2.0 and parallel MultiWoZ 2.1 datasets show that ourproposed CLCL-DST outperforms existing state-of-the-art methods by a large margin, demon-strating the effectiveness of CLCL-DST.”
Anthology ID:
2023.ccl-1.54
Volume:
Proceedings of the 22nd Chinese National Conference on Computational Linguistics
Month:
August
Year:
2023
Address:
Harbin, China
Editors:
Maosong Sun, Bing Qin, Xipeng Qiu, Jing Jiang, Xianpei Han
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
624–625
Language:
English
URL:
https://aclanthology.org/2023.ccl-1.54
DOI:
Bibkey:
Cite (ACL):
Xiang Yu, Zhang Ting, Di Hui, Huang Hui, Li Chunyou, Ouchi Kazushige, Chen Yufeng, and Xu Jinan. 2023. Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 624–625, Harbin, China. Chinese Information Processing Society of China.
Cite (Informal):
Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning (Yu et al., CCL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.ccl-1.54.pdf