Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence

Mengxiao Song, Bowen Yu, Li Quangang, Wang Yubin, Tingwen Liu, Hongbo Xu


Abstract
Multi-intent detection and slot filling joint model attracts more and more attention since it can handle multi-intent utterances, which is closer to complex real-world scenarios. Most existing joint models rely entirely on the training procedure to obtain the implicit correlation between intents and slots. However, they ignore the fact that leveraging the rich global knowledge in the corpus can determine the intuitive and explicit correlation between intents and slots. In this paper, we aim to make full use of the statistical co-occurrence frequency between intents and slots as prior knowledge to enhance joint multiple intent detection and slot filling. To be specific, an intent-slot co-occurrence graph is constructed based on the entire training corpus to globally discover correlation between intents and slots. Based on the global intent-slot co-occurrence, we propose a novel graph neural network to model the interaction between the two subtasks. Experimental results on two public multi-intent datasets demonstrate that our approach outperforms the state-of-the-art models.
Anthology ID:
2022.emnlp-main.543
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7967–7977
Language:
URL:
https://aclanthology.org/2022.emnlp-main.543
DOI:
10.18653/v1/2022.emnlp-main.543
Bibkey:
Cite (ACL):
Mengxiao Song, Bowen Yu, Li Quangang, Wang Yubin, Tingwen Liu, and Hongbo Xu. 2022. Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7967–7977, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence (Song et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.543.pdf
Software:
 2022.emnlp-main.543.software.zip
Dataset:
 2022.emnlp-main.543.dataset.zip