Computer Science

CLC number: TP311

The Joint Model of Multi-Intent Detection and Slot Filling Based on Bidirectional Interaction Structure

基于双向交互结构的多意图识别与槽位填充联合模型

¹ School of Digital Industry, Jiangxi Normal University, Shangrao 334000, Jiangxi, China
² School of Computer Information Engineering, Jiangxi Normal University, Nanchang 330022, Jiangxi, China
³ Jiangxi Provincial Key Laboratory for High Performance Computing, Jiangxi Normal University, Nanchang 330022, Jiangxi, China
⁴ State International Science and Technology Cooperation Base of Networked Supporting Software, Jiangxi Normal University, Nanchang 330022, Jiangxi, China

^† Corresponding author. E-mail: zhengkang2005@iscas.ac.cn

Received: 28 July 2024

Abstract

Intent detection and slot filling are two important components of natural language understanding. Because their relevance, joint training is often performed to improve performance. Existing studies mostly use a joint model of multi-intent detection and slot-filling with unidirectional interaction, which improves the overall performance of the model by fusing the intent information in the slot-filling part. On this basis, in order to further improve the overall performance of the model by exploiting the correlation between the two, this paper proposes a joint multi-intent detection and slot-filling model based on a bidirectional interaction structure, which fuses the intent encoding information in the encoding part of slot filling and fuses the slot decoding information in the decoding part of intent detection. Experimental results on two public multi-intent joint training datasets, MixATIS and MixSNIPS, show that the bidirectional interaction structure proposed in this paper can effectively improve the performance of the joint model. In addition, in order to verify the generalization of the bidirectional interaction structure between intent and slot, a joint model for single-intent scenarios is proposed on the basis of the model in this paper. This model also achieves excellent performance on two public single-intent joint training datasets, CAIS and SNIPS.

摘要

意图识别与槽位填充是自然语言理解的两个重要组成部分，由于两者的相关性, 所以常进行联合训练提高性能。现有研究多是采用单向交互的多意图识别与槽位填充联合模型，通过在槽位填充部分融合意图信息提高了模型整体性能。为了进一步利用两者的相关性提高模型整体性能，本文提出了基于双向交互结构的多意图识别与槽位填充联合模型，在槽位填充编码部分融合了意图编码信息，在意图识别解码部分融合了槽位解码信息。在MixATIS和MixSNIPS两个公共多意图联合训练数据集上的实验结果表明，该双向交互结构能有效提高联合模型的性能。此外，为了验证意图与槽位双向交互结构的泛化性，在本文模型的基础上提出了针对单意图场景的联合模型，在CAIS和SNIPS两个公共单意图联合训练数据集上也取得了优异的性能。