Hybrid Neural Network Models for Human-machine Dialogue Intention Classification

被引：0
作者：
Zhou J.-Z. [1 ]
Zhu Z.-K. [1 ]
He Z.-Q. [1 ]
Chen W.-L. [1 ]
Zhang M. [1 ]
机构：
[1] Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou
来源：
Ruan Jian Xue Bao/Journal of Software | 2019年 / 30卷 / 11期
基金：
中国国家自然科学基金;
关键词：
Attention mechanism; Capsule network; Hybrid model; Intention classification; Language model;
D O I：
10.13328/j.cnki.jos.005862
中图分类号：
学科分类号：
摘要：
With the development of human-machine dialogue, it is of great significance for the computer to accurately understand the user's query intention in human-machine dialogue systems. Intention classification aims at judging the user's intention in human machine dialogue and improves the accuracy and naturalness of the human machine dialogue system. This study first analyzes the advantages and disadvantages of multiple classification models in the intention classification task. On this basis, this study proposes a hybrid neural network model to comprehensively utilize the diversity outputs of multiple deep network models. To further improve the perfoance, the language model embedding is used in the input feature preprocessing and the semantic mining ability possessed for the hybrid network which can effectively improve the expression ability of the model. The proposed model achieves 2.95% and 3.85% performance improvement on the two data sets respectively compared to the best benchmark model. The proposed model also achieves the top performance in a shared task. © Copyright 2019, Institute of Software, the Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：3313 / 3325
页数：12
相关论文
共 28 条
  • [1] Morbini F., De-Vault D., Sagae K., Gerten J., Nazarian A., Traum D., FLoReS: A forward looking, reward seeking, dialogue manager, Natural Interaction with Robots, Knowbots and Smartphones, pp. 313-325, (2012)
  • [2] Tur G., Celikyilmaz A., Hakkani-Tur D., Latent semantic modeling for slot filling in conversational understanding, Proc. of the 2013 IEEE Int'l Conf. on Acoustics, Speech, and Signal Processing, pp. 8307-8311, (2013)
  • [3] Eyben F., Wollmer M., Graves A., Schuller B., Douglas-Cowie E., Cowie R., On-line emotion recognition in a 3-D activation-valence-time continuum using acoustic and linguistic cues, Journal on Multimodal User Interfaces, 3, 1-2, pp. 7-12, (2010)
  • [4] Yang Z., Yang D., Dyer C., He X., Smola A., Hovy E., Hierarchical attention networks for document classification, Proc. of the 2016 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480-1489, (2016)
  • [5] Lai S., Xu L., Liu K., Zhao J., Recurrent convolutional neural networks for text classification, Proc. of the 29th AAAI Conf. on Artificial Intelligence, pp. 2267-2273, (2015)
  • [6] Li C., Chai Y.M., Nan X.F., Gao M.L., Research on problem classification method based on deep learning, Computer Science, 43, 12, pp. 115-119, (2016)
  • [7] Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., Rabinovich A., Going deeper with convolutions, Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1-9, (2015)
  • [8] Peters M.E., Neumann M., Iyyer M., Gardner M., Clark C., Lee K., Zettlemoyer L., Deep contextualized word representations, (2018)
  • [9] Mathew J., Radhakrishnan D., An FIR digital filter using onehot coded residue representation, Proc. of the 10th European Signal Processing Conf., pp. 1-4, (2000)
  • [10] Irsoy O., Cardie C., Opinion mining with deep recurrent neural networks, Proc. of the 2014 Conf. on Empirical Methods in Natural Language Processing (EMNLP), pp. 720-728, (2014)
123