A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding

by   Zhihong Zhu, et al.

Multi-intent detection and slot filling joint models are gaining increasing traction since they are closer to complicated real-world scenarios. However, existing approaches (1) focus on identifying implicit correlations between utterances and one-hot encoded labels in both tasks while ignoring explicit label characteristics; (2) directly incorporate multi-intent information for each token, which could lead to incorrect slot prediction due to the introduction of irrelevant intent. In this paper, we propose a framework termed DGIF, which first leverages the semantic information of labels to give the model additional signals and enriched priors. Then, a multi-grain interactive graph is constructed to model correlations between intents and slots. Specifically, we propose a novel approach to construct the interactive graph based on the injection of label semantics, which can automatically update the graph to better alleviate error propagation. Experimental results show that our framework significantly outperforms existing approaches, obtaining a relative improvement of 13.7 overall accuracy.


page 1

page 2

page 3

page 4


TD-GIN: Token-level Dynamic Graph-Interactive Network for Joint Multiple Intent Detection and Slot Filling

Intent detection and slot filling are two main tasks for building a spok...

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

Recent graph-based models for joint multiple intent detection and slot f...

Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling

Recent joint multiple intent detection and slot filling models employ la...

A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding

Multi-Intent Spoken Language Understanding (SLU), a novel and more compl...

Multi-grained Label Refinement Network with Dependency Structures for Joint Intent Detection and Slot Filling

Slot filling and intent detection are two fundamental tasks in the field...

User Information Augmented Semantic Frame Parsing using Coarse-to-Fine Neural Networks

Semantic frame parsing is a crucial component in spoken language underst...

Please sign up or login with your details

Forgot password? Click here to reset