AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling

Libo Qin, Xiao Xu, Wanxiang Che, Ting Liu


Abstract
In real-world scenarios, users usually have multiple intents in the same utterance. Unfortunately, most spoken language understanding (SLU) models either mainly focused on the single intent scenario, or simply incorporated an overall intent context vector for all tokens, ignoring the fine-grained multiple intents information integration for token-level slot prediction. In this paper, we propose an Adaptive Graph-Interactive Framework (AGIF) for joint multiple intent detection and slot filling, where we introduce an intent-slot graph interaction layer to model the strong correlation between the slot and intents. Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information, making a fine-grained intent information integration for the token-level slot prediction. Experimental results on three multi-intent datasets show that our framework obtains substantial improvement and achieves the state-of-the-art performance. In addition, our framework achieves new state-of-the-art performance on two single-intent datasets.
Anthology ID:
2020.findings-emnlp.163
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1807–1816
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.163
DOI:
10.18653/v1/2020.findings-emnlp.163
Bibkey:
Cite (ACL):
Libo Qin, Xiao Xu, Wanxiang Che, and Ting Liu. 2020. AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1807–1816, Online. Association for Computational Linguistics.
Cite (Informal):
AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling (Qin et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.163.pdf
Code
 LooperXX/AGIF
Data
MixATISATISSNIPS