AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
This addresses a key limitation in SLU for real-world applications where utterances contain multiple intents, improving accuracy for tasks like virtual assistants.
The paper tackles the problem of joint multiple intent detection and slot filling in spoken language understanding, where users often have multiple intents in a single utterance, and achieves state-of-the-art performance on three multi-intent datasets and two single-intent datasets.
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.