Work

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

Year: 2023

Type: conference-paper

Abstract: 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 results1show that our framework significantly outperforms existing approaches, obtaining a relative improvement of 6.5% over the previous best model on the MixATIS dataset in overall accuracy.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49357.2023.10095809

Authors: Zhihong Zhu, Weiyuan Xu, Xuxin Cheng, Tengtao Song, Yuexian Zou

Institution: Peking University

Language: English

Topic: Speech and dialogue systems

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Natural Science Foundation of China

Awards: G1739072399, G893883872