Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs

TL;DR

This paper introduces Co-guiding Net, a novel two-stage model that enables mutual guidance between intent detection and slot filling tasks using heterogeneous graphs, significantly improving performance over previous methods.

Contribution

The paper proposes a two-stage framework with heterogeneous graph attention networks for mutual guidance between intent detection and slot filling, addressing unidirectional guidance and homogeneous graph limitations.

Findings

Achieves 19.3% relative improvement on MixATIS dataset

Outperforms existing models by a large margin

Effectively models relations with heterogeneous graphs

Abstract

Recent graph-based models for joint multiple intent detection and slot filling have obtained promising results through modeling the guidance from the prediction of intents to the decoding of slot filling. However, existing methods (1) only model the \textit{unidirectional guidance} from intent to slot; (2) adopt \textit{homogeneous graphs} to model the interactions between the slot semantics nodes and intent label nodes, which limit the performance. In this paper, we propose a novel model termed Co-guiding Net, which implements a two-stage framework achieving the \textit{mutual guidances} between the two tasks. In the first stage, the initial estimated labels of both tasks are produced, and then they are leveraged in the second stage to model the mutual guidances. Specifically, we propose two \textit{heterogeneous graph attention networks} working on the proposed two \textit{heterogeneous semantics-label graphs}, which effectively represent the relations among the semantics nodes and label nodes. Experiment results show that our model outperforms existing models by a large margin, obtaining a relative improvement of 19.3\% over the previous best model on MixATIS dataset in overall accuracy.