Joint Intent Detection Model for Task-oriented Human-Computer Dialogue System using Asynchronous Training
Open Access
- 9 May 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (5) , 1-17
Abstract
How to accurately understand low-resource languages is the core of the task-oriented human-computer dialogue system. Language understanding consists of two sub-tasks, i.e., intent detection and slot filling. Intent detection still faces challenges due to semantic ambiguity and implicit intentions with users’ input. Moreover, separately modeling intent detection and slot filling significantly decrease the correctness and relevance between questions and answers. To address these issues, we propose a joint intent detection method using asynchronous training strategy. The proposed method firstly encodes local text information extracted by CNN and relationship information among words emphasized by attention structure. Later, a joint intent detection model with asynchronous training strategy is proposed by either fusing hidden states of intent detection and slot filling layers, or adopting the key information to fine-tune the whole network, greatly increasing the relevance of intent detection and slot filling subtasks. The accuracy achieved by the proposed method tested on an open-source airline travel dataset and a self-collected electricity service dataset, i.e., ATIS and ECSF, are 97.49% and 89.68%, respectively, which proves the effectiveness of joint learning and asynchronous training.Keywords
Funding Information
- National Natural Science Foundation of China (62172438, 61702160)
- National Key R&D Program of China (2021YFB3900601)
- Key Project of Shenzhen City Special Fund for Fundamental Research (202208183000751)
- Key Laboratory of AI and Information Processing
- Education Department of Guangxi Zhuang Autonomous Region (2022GXZDSY014)
- Fundamental Research Funds for the Central Universities (B220202074)
- Fundamental Research Funds for the Central Universities, JLU
- Joint Foundation of the Ministry of Education (8091B022123)
This publication has 15 references indexed in Scilit:
- An Evaluation of Chinese Human-Computer Dialogue TechnologyData Intelligence, 2021
- Self-attention-based conditional random fields latent variables model for sequence labelingPattern Recognition Letters, 2021
- Zero-shot User Intent Detection via Capsule Neural Networks2018
- Slot-Gated Modeling for Joint Slot Filling and Intent Prediction2018
- Long Short-Term Memory-Networks for Machine Reading2016
- Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling2016
- Effective Approaches to Attention-based Neural Machine Translation2015
- Convolutional Neural Networks for Sentence Classification2014
- Triangular-Chain Conditional Random FieldsIEEE Transactions on Audio, Speech, and Language Processing, 2008
- Learning question classifiers: the role of semantic informationNatural Language Engineering, 2005