Research on power customer service composite intention recognition based on dependency syntax and graph attention network

With the rapid development of computer technology, intelligent task-based dialogue systems emerge in endlessly. Among them, intention recognition is an essential task of natural language understanding in human-computer dialogue. Aiming at the difficulty of composite intention recognition in the powe...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) pp. 1249 - 1255
Main Authors Lintan, Sun, Wei, Zhao, Chenfei, Wang, Shuo, Zhang, Huimin, Zhang, Ziqian, Li, Yumeng, Zhang, Yan, Zhang, Min, Li, Liyang, Xu
Format Conference Proceeding
LanguageEnglish
Published IEEE 24.02.2023
Subjects
Analytical models
Attention network
Customer services
Dependency parsing
Electrical engineering
Intention recognition
Natural language processing
Neural networks
Power customer service
Syntactics
Text recognition
Online AccessGet full text

Cover

More Information
Summary:With the rapid development of computer technology, intelligent task-based dialogue systems emerge in endlessly. Among them, intention recognition is an essential task of natural language understanding in human-computer dialogue. Aiming at the difficulty of composite intention recognition in the power customer service field, this paper combines the advantages of dependency syntax analysis and graph attention neural network. It adopts a graph attention neural network model integrating the dependency matrix. This model uses dependency information and its relationship types for context information modeling, distinguishes the importance of context features through the attention mechanism, and has flexible calculation, high accuracy, and good generalization.
DOI:10.1109/EEBDA56825.2023.10090599