Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling
This work addresses a domain-specific problem in natural language processing for improving dialogue systems, representing a novel method for a known bottleneck.
The paper tackled the problem of joint multiple intent detection and slot filling by addressing the neglect of label dependencies and task correlations in existing models, resulting in a novel model, ReLa-Net, that achieved over 20% improvement in overall accuracy on the MixATIS dataset.
Recent joint multiple intent detection and slot filling models employ label embeddings to achieve the semantics-label interactions. However, they treat all labels and label embeddings as uncorrelated individuals, ignoring the dependencies among them. Besides, they conduct the decoding for the two tasks independently, without leveraging the correlations between them. Therefore, in this paper, we first construct a Heterogeneous Label Graph (HLG) containing two kinds of topologies: (1) statistical dependencies based on labels' co-occurrence patterns and hierarchies in slot labels; (2) rich relations among the label nodes. Then we propose a novel model termed ReLa-Net. It can capture beneficial correlations among the labels from HLG. The label correlations are leveraged to enhance semantic-label interactions. Moreover, we also propose the label-aware inter-dependent decoding mechanism to further exploit the label correlations for decoding. Experiment results show that our ReLa-Net significantly outperforms previous models. Remarkably, ReLa-Net surpasses the previous best model by over 20\% in terms of overall accuracy on MixATIS dataset.