HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding

Bo Zheng, Zhouyang Li, Fuxuan Wei, Qiguang Chen, Libo Qin, Wanxiang Che


Abstract
Multilingual spoken language understanding (SLU) consists of two sub-tasks, namely intent detection and slot filling. To improve the performance of these two sub-tasks, we propose to use consistency regularization based on a hybrid data augmentation strategy. The consistency regularization enforces the predicted distributions for an example and its semantically equivalent augmentation to be consistent. We conduct experiments on the MASSIVE dataset under both full-dataset and zero-shot settings. Experimental results demonstrate that our proposed method improves the performance on both intent detection and slot filling tasks. Our system ranked 1st in the MMNLU-22 competition under the full-dataset setting.
Anthology ID:
2022.mmnlu-1.4
Volume:
Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Jack FitzGerald, Kay Rottmann, Julia Hirschberg, Mohit Bansal, Anna Rumshisky, Charith Peris, Christopher Hench
Venue:
MMNLU
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
35–41
Language:
URL:
https://aclanthology.org/2022.mmnlu-1.4
DOI:
10.18653/v1/2022.mmnlu-1.4
Bibkey:
Cite (ACL):
Bo Zheng, Zhouyang Li, Fuxuan Wei, Qiguang Chen, Libo Qin, and Wanxiang Che. 2022. HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding. In Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22), pages 35–41, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding (Zheng et al., MMNLU 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.mmnlu-1.4.pdf
Video:
 https://aclanthology.org/2022.mmnlu-1.4.mp4