基于混合神经网络的问题分类方法

doi:10.3969/j.issn.1006-2475.2018.09.001

计算机与现代化

• 人工智能 • 下一篇

基于混合神经网络的问题分类方法

(1.中国科学院大学电子电气与通信工程学院,北京100049; 2.中国科学院电子学研究所,北京100190; 3.中国科学院空间信息处理与应用系统技术重点实验室，北京100190)

收稿日期:2018-03-09 出版日期:2018-09-29 发布日期:2018-09-30
作者简介:陈柯锦(1993-)，男，重庆人，中国科学院大学电子电气与通信工程学院、中国科学院电子学研究所硕士研究生，研究方向：问答系统，知识图谱; 许光銮(1978-)，男，研究员，博士，研究方向：地理空间信息挖掘与应用; 郭智(1975-)，男，研究员，博士，研究方向：数据挖掘，知识工程; 梁霄(1981-)，男，助理研究员，博士，研究方向：复杂网络，知识工程，问答系统。
基金资助:
国家自然科学基金资助项目(61725105, 61331017)

Question Classification Based on Hybrid Neural Network Model

(1. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China;
2. Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
3. Key Laboratory of Technology in Geo-Spatial Information Processing and Application System,
Chinese Academy of Sciences, Beijing 100190, China)

Received:2018-03-09 Online:2018-09-29 Published:2018-09-30

摘要/Abstract

摘要： 自动问答系统对用户自然语言方式提出的问题，给出快速准确的答案，引起了学术界与工业界的广泛关注。问题分类任务通过自动判断问题类型，对提高问答系统回答问题的准确率具有重要意义。本文利用问题和答案的上下文信息，结合卷积神经网络和循环神经网络各自的优势，提出一种混合深度学习模型。除此之外，为了增强问题特征的表达能力，该模型引入注意力机制，提升模型的泛化能力。在360问答数据集进行对比实验验证，实验表明，本文模型相比于传统方法提升了1.6%~5.6%。

关键词: 问题分类, 联合表示, 深度学习, 注意力机制

Abstract: The automatic question answering system gives fast and accurate answers to the questions proposed by the users in natural language, arousing widespread concern in academia and industry. By automatically determining the type of question, question classification task is of great significance to improve the accuracy of the question answering system. Based on the contextual information of the question and answer, combined with the respective advantages of convolutional neural networks and recurrent neural networks, this paper proposes a hybrid deep learning model. In addition, in order to strengthen the representation capacity of the question, this model adopts attention mechanism and enhances the generalization ability of the model. In this paper, we conduct a comparative experiment on 360 QA datasets, results show that this model has improved 1.6%~5.6% compared with the traditional method.

Key words: question classification, joint representation, deep learning, attention mechanism

中图分类号:

TP391

陈柯锦1,2,3，许光銮2,3，郭智2,3，梁霄2,3. 基于混合神经网络的问题分类方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.09.001.

CHEN Ke-jin1,2,3, XU Guang-luan2,3, GUO Zhi2,3, LIANG Xiao2,3. Question Classification Based on Hybrid Neural Network Model[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.09.001.

参考文献

［1］ Joachims T. Text categorization with support vector machines: Learning with many relevant features［C］// Proceedings of the 10th European Conference on Machine Learning. 1998:137-142.
［2］ Aikawa N, Sakai T, Yamana H. Community QA question classification: Is the asker looking for subjective answers or not?［J］. IPSJ Online Transactions, 2011,4:160-168.
［3］ Li Xin, Roth D. Learning question classifiers［C］// Proceedings of the 19th International Conference on Computational Linguistics. 2002,1:556-562.
［4］ Zhang D, Lee W S. Question classification using support vector machines［C］// Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2003:26-32.
［5］ Kim Y. Convolutional neural networks for sentence classification［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014:1746-1751.
［6］ Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition［J］. Proceedings of the IEEE, 1998,86(11):2278-2324.
［7］ Ma Mingbo, Huang Liang, Xiang Bing, et al. Group sparse CNNs for question classification with answer sets［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 2017,2:335-340.
［8］ Gers F A, Schmidhuber J, Cummins F. Learning to forget: Continual prediction with LSTM［J］. Neural Computation, 2000,12(10):2451-2471.
［9］ Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate［DB/OL］. https://arxiv.org/pdf/1409.0473v7.pdf, 2016-05-19.
［10］Ding Zixiang, Xia Rui, Yu Jianfei, et al. Densely Connected Bidirectional LSTM with Applications to Sentence Classification［DB/OL］. https://arxiv.org/pdf/1802.00889v1.pdf, 2018-02-03.
［11］Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures［J］. Neural Networks, 2005,18(5-6):602-610.
［12］Yang Zichao, Yang Diyi, Dyer C, et al. Hierarchical attention networks for document classification［C］// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016:1480-1489.
［13］Jain L C, Medsker L R. Recurrent Neural Networks: Design and Applications［M］. CRC Press, 1999.
［14］Hochreiter S, Schmidhuber J. Long short-term memory［J］. Neural Computation, 1997,9(8):1735-1780.
［15］Graves A. Generating Sequences with Recurrent Neural Networks［DB/OL］. https://arxiv.org/pdf/1308.0850v5.pdf, 2014-06-05.
［16］张栋,李寿山,王晶晶. 基于问题与答案联合表示学习的半监督问题分类方法［J］. 中文信息学报, 2017,31(1):1-7.
［17］Mikolov T, Sutskever I, Chen Kai, et al. Distributed representations of words and phrases and their compositionality［C］// Proceedings of the 2013 Advances in Neural Information Processing Systems. 2013:3111-3119.
［18］Prechelt L. Early stopping-but when?［M］// Neural Networks: Tricks of the Trade. Springer, 1998:55-69.
［19］Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting［J］. Journal of Machine Learning Research, 2014,15(1):1929-1958.

[1]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[2]	林启钊, 彭志平, 郭棉, 崔得龙. 基于双向多步预测的炉管温度场重构方法[J]. 计算机与现代化, 2024, 0(01): 53-58.
[3]	李亚平, 王军防, 余红梅, 窦一民, 肖媛, 田继林. Regformer：基于稀疏注意力的输油管道水力压降预测方法[J]. 计算机与现代化, 2024, 0(01): 59-66.
[4]	胡崇佳, 刘金洲, 方立. 基于无监督域适应的室外点云语义分割[J]. 计算机与现代化, 2024, 0(01): 74-79.
[5]	林威. 基于自监督学习和数据回放的新闻推荐模型增量学习方法[J]. 计算机与现代化, 2023, 0(12): 1-6.
[6]	梁天恺, 黄康华, 刘凯航, 兰岚, 曾碧. 基于双向同态加密的深度联邦图片分类方法[J]. 计算机与现代化, 2023, 0(12): 36-40.
[7]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[8]	张浩洋, 尹梓名, 乐珺怡, 沈达聪, 束翌俊, 杨自逸, 孔祥勇, 龚伟. 3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型[J]. 计算机与现代化, 2023, 0(12): 59-66.
[9]	张伯泉, 麦海鹏, 陈嘉敏, 逄锦聚. 基于高灰度值注意力机制的脑白质高信号分割[J]. 计算机与现代化, 2023, 0(12): 67-75.
[10]	宁娟, 周庆华, 曾小为. 改进YOLOv7算法在西林瓶轧盖缺陷检测中的应用[J]. 计算机与现代化, 2023, 0(12): 82-86.
[11]	王宇航, 董宝良, 公超, 尚真真, 姚康宁. 基于意图识别的空中群目标动态威胁评估[J]. 计算机与现代化, 2023, 0(12): 100-104.
[12]	罗明杰, 冯开平. 基于沙漏结构与注意力机制的轻量级人脸表情识别方法[J]. 计算机与现代化, 2023, 0(11): 89-94.
[13]	马泽宇, 叶宁, 徐康, 王甦, 王汝传, . 基于FMCW雷达和ResNeSt-GRU的行为识别方法[J]. 计算机与现代化, 2023, 0(11): 101-107.
[14]	张嘉琪, 徐啟蕾. 基于NAM-YOLO网络的苹果缺陷检测算法[J]. 计算机与现代化, 2023, 0(10): 53-58.
[15]	李延满, 王必恒, 赵羚焱. 基于轻量化YOLOv5的安全帽检测[J]. 计算机与现代化, 2023, 0(10): 59-64.

基于混合神经网络的问题分类方法

Question Classification Based on Hybrid Neural Network Model

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价