论文标题
组比个人更好：利用标签拓扑和标签关系，用于联合多重意图检测和插槽填充
Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling
论文作者
论文摘要
最近的关节多重意图检测和插槽填充模型采用标签嵌入来实现语义标签的相互作用。但是，他们将所有标签和标签嵌入视为不相关的个体，而忽略了其中的依赖性。此外，他们独立地执行了这两个任务的解码，而无需利用它们之间的相关性。因此，在本文中，我们首先构建了包含两种拓扑结构的异质标签图（HLG）：（1）基于标签的共发生模式和层次结构的统计依赖性； （2）标签节点之间的丰富关系。然后，我们提出了一种称为Rela-Net的新型模型。它可以捕获HLG标签之间的有益相关性。标签相关性被利用以增强语义标记的相互作用。此外，我们还提出了标签感知的相互依赖性解码机制，以进一步利用标签相关性进行解码。实验结果表明，我们的Rela-NET明显优于先前的模型。值得注意的是，Rela-Net在Mixatis数据集的总体准确性方面超过20 \％以上的最佳模型。
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.
