DC-Instruct: An Effective Framework for Generative Multi-intent Spoken Language Understanding

Bowen Xing, Lizi Liao, Minlie Huang, Ivor Tsang


Abstract
In the realm of multi-intent spoken language understanding, recent advancements have leveraged the potential of prompt learning frameworks. However, critical gaps exist in these frameworks: the lack of explicit modeling of dual-task dependencies and the oversight of task-specific semantic differences among utterances. To address these shortcomings, we propose DC-Instruct, a novel generative framework based on Dual-task Inter-dependent Instructions (DII) and Supervised Contrastive Instructions (SCI). Specifically, DII guides large language models (LLMs) to generate labels for one task based on the other task’s labels, thereby explicitly capturing dual-task inter-dependencies. Moreover, SCI leverages utterance semantics differences by guiding LLMs to determine whether a pair of utterances share the same or similar labels. This can improve LLMs on extracting and discriminating task-specific semantics, thus enhancing their SLU reasoning abilities. Extensive experiments on public benchmark datasets show that DC-Instruct markedly outperforms current generative models and state-of-the-art methods, demonstrating its effectiveness in enhancing dialogue language understanding and reasoning.
Anthology ID:
2024.emnlp-main.804
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14520–14534
Language:
URL:
https://aclanthology.org/2024.emnlp-main.804
DOI:
Bibkey:
Cite (ACL):
Bowen Xing, Lizi Liao, Minlie Huang, and Ivor Tsang. 2024. DC-Instruct: An Effective Framework for Generative Multi-intent Spoken Language Understanding. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14520–14534, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
DC-Instruct: An Effective Framework for Generative Multi-intent Spoken Language Understanding (Xing et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.804.pdf