Zero-Shot Spoken Language Understanding via Large Language Models: A Preliminary Study

Zhihong Zhu, Xuxin Cheng, Hao An, Zhichang Wang, Dongsheng Chen, Zhiqi Huang


Abstract
Zero-shot Spoken Language Understanding (SLU) aims to enable task-oriented dialogue systems to understand user needs without training data. Challenging but worthwhile, zero-shot SLU reduces the time and effort that data labeling takes. Recent advancements in large language models (LLMs), such as GPT3.5 and ChatGPT, have shown promising results in zero-shot settings, which motivates us to explore prompt-based methods. In this study, we investigate whether strong SLU models can be constructed by directly prompting LLMs. Specifically, we propose a simple yet effective two-stage framework dubbed GPT-SLU, which transforms the SLU task into a question-answering problem. Powered by multi-stage mutual guided prompts, GPT-SLU can leverage the correlations between two subtasks in SLU to achieve better predictions, which is greatly explored in the traditional fine-tuning paradigm. Experimental results on three SLU benchmark datasets demonstrate the significant potential of LLMs for zero-shot SLU. Comprehensive analyses validate the effectiveness of our proposed framework and also indicate that there is still room for further improvement of LLMs in SLU scenarios.
Anthology ID:
2024.lrec-main.1554
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
17877–17883
Language:
URL:
https://aclanthology.org/2024.lrec-main.1554
DOI:
Bibkey:
Cite (ACL):
Zhihong Zhu, Xuxin Cheng, Hao An, Zhichang Wang, Dongsheng Chen, and Zhiqi Huang. 2024. Zero-Shot Spoken Language Understanding via Large Language Models: A Preliminary Study. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17877–17883, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Zero-Shot Spoken Language Understanding via Large Language Models: A Preliminary Study (Zhu et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1554.pdf