End-to-end multi-task optimization model for task-based dialogue systems

被引：0

作者：

Zhao F. ^{[1
,2
,3
]}

Qiu M. ^{[1
,3
]}

Li X. ^{[1
,3
]}

Sun Y. ^{[1
,3
]}

Yang Z. ^{[1
,3
]}

机构：

[1] School of Information Science and Engineering, Yanshan University, Qinhuangdao

[2] School of Information Science and Engineering, Xinjiang University of Science and Technology, Korla

[3] The Key Laboratory for Software Engineering of Hebei Province, Qinhuangdao

来源：

Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2023年 / 29卷 / 11期

关键词：

dialogue system; human-machine interaction; intent detection; slot filling; Stack-Propagation framwork;

D O I：

10.13196/j.cims.2022.0401

中图分类号：

学科分类号：

摘要：

In the natural language understanding module, there are two tasks of intent detection and slot filling, and there is a strong correlation between the two tasks that the generation of slot information is highly dependent on the intent information. However, most of the existing works regard it as two independent tasks to achieve, resulting in that the accuracy of the dialogue system cannot be further improved. To this end, aiming at the correlation information between the intent detection task and the slot filling task in the dialogue system, on the basis of the existing work, an end-to-end network model based on the idea of Stack-Propagation was proposed. The idea of the Stack-Propagation framework in the decoder stage was borrowed and improved, which added the result of intent detection to the input of the slot filling task, and used the result of the intent detection to further guide the slot filling task. Through experiments on SMD dataset, it was proved that the model could not only make full use of the correlation information between the intent detection task and the slot filling task, but also achieve the effect of mutual promotion through joint learning, and finally effectively improve the accuracy of the dialogue system. © 2023 CIMS. All rights reserved.

引用

页码：3592 / 3599

页数：7

共 29 条

[1] Chaomin MA, ZHAO Danhua, XIN Hao, Design of human-machine interface for intelligent equipment based on user experience [J], Computer Integrated Manufacturing Systems
[2] DILEK H T, GOKHAN T, ASLI C, Et al., Multi-domain joint semantic frame parsing using bi-directional RNN-LSTM
[3] LIU B, LANE I., Attention-based recurrent neural network models for joint intent detection and slot filling
[4] GOO C, GAO G, HSU Y K., Et al., Slot-gated modeling for joint slot filling and intent prediction
[5] LI C L, LI L, A self-attentive model with gate mechanism for spoken language understanding
[6] QIN L B, CHE W, LI Y M, Et al., A stack-propagation framework with token-level intent detection for spoken language understandlng
[7] WEN T H., VANDYKE D, MRKS1C N, Et al., A network-based end-to-end trainable task-oriented dialogue system
[8] BORDES A, BOUREAU Y L, WESTON J., Learning end-to-end goal-oriented dialog
[9] ZHAO T C, ESKENAZI M., Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning
[10] WU C S, XIONG C M, Global-to-local memory pointer networks for task-oriented dialogue

← 1 2 3 →