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

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.

PDF Abstract Findings of 2020 PDF Findings of 2020 Abstract

Datasets


Introduced in the Paper:

MixATIS MixSNIPS

Used in the Paper:

ATIS SNIPS

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Intent Detection ATIS AGIF Accuracy 97.1 # 13
Slot Filling ATIS AGIF F1 0.96 # 6
Slot Filling MixSNIPS AGIF Micro F1 94.5 # 15
Intent Detection MixSNIPS AGIF Accuracy 96.5 # 12
f1 macro 98.6 # 1
Semantic Frame Parsing MixSNIPS AGIF Accuracy 76.4 # 12
Slot Filling SNIPS AGIF F1 94.8 # 4
Intent Detection SNIPS AGIF Accuracy 98.1 # 4

Methods


No methods listed for this paper. Add relevant methods here