基于卷积神经网络的中文人物关系抽取方法

doi:10.3969/j.issn.1006-2475.2018.09.004

计算机与现代化 ›› 2018, Vol. 0 ›› Issue (09): 17-.doi: 10.3969/j.issn.1006-2475.2018.09.004

基于卷积神经网络的中文人物关系抽取方法

(1.中国电建集团华中电力设计研究院有限公司，河南郑州450007;2.华北电力大学电子与通信工程系，河北保定071003)

收稿日期:2018-04-19 出版日期:2018-09-29 发布日期:2018-09-30
作者简介:司文豪(1968-),女,河南郑州人,中国电建集团华中电力设计研究院有限公司高级工程师,本科,研究方向:电力信息与通信技术; 贾雷萍(1991-),女,华北电力大学电子与通信工程系硕士研究生,研究方向:信息处理; 戚银城(1968-),男,教授,博士,研究方向:电力信息技术。

Chinese Personal Relation Extraction Method Based on Convolutional Neural Network

(1. Central China Electric Power Engineering Corporation Limited, Power China, Zhengzhou 450007, China;
2. Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China)

Received:2018-04-19 Online:2018-09-29 Published:2018-09-30

摘要/Abstract

摘要： 针对基于机器学习的人物关系抽取需要人工选取特征的问题，提出一种基于卷积神经网络的中文人物关系抽取方法。采用搜狗实验室公开的中文全网新闻语料库来训练Word2vec模型，得到基于分布式表示的词向量表达，并完成了对百度百科数据集的词向量转化工作。设计一种基于经典CNN模型的中文人物关系抽取系统方案，用CNN模型自动提取特征并进行人物关系的分类，实现了5类常见人物关系的提取，准确率达到92.87%，平均召回率达到86.92%。实验结果表明，该方法无需人工构建复杂特征即可得到较好的人物关系抽取效果。

关键词: 文本挖掘, 人物关系抽取, 卷积神经网络, 分类, 词向量特征

Abstract: Focused on the problem that the features need to be selected manually in personal relation extraction based on machine learning, a Chinese personal relation extraction method based on convolutional neural networks is proposed. The Word2vec model is trained by the Internet Chinese news corpus of Sogou Lab, and the expression of word vector based on distributed representation is obtained, and the transformation of the word vector for the Baidu encyclopedia data set is completed. A Chinese personal relation extraction system based on the classic CNN model is designed. The features are automatically extracted and the personal relation is classified by the CNN model. The accuracy rate reaches to 92.87%, and the average recall rate reaches to 86.92% in extraction of 5 kinds of personal relation. Experimental results show that this method does not need to construct complex features artificially, and it can get a better effect in personal relation extraction.

Key words: text mining, personal relation extraction, convolutional neural network, classification, word vector feature

中图分类号:

TP391

司文豪1，贾雷萍2，戚银城2. 基于卷积神经网络的中文人物关系抽取方法[J]. 计算机与现代化, 2018, 0(09): 17-.

SI Wen-hao1, JIA Lei-ping2, QI Yin-cheng2. Chinese Personal Relation Extraction Method Based on Convolutional Neural Network[J]. Computer and Modernization, 2018, 0(09): 17-.

参考文献

［1］罗永莲,赵昌垣,贾玉芳,等. 基于朴素贝叶斯Web新闻内容的抽取方法［J］. 计算机与现代化, 2016(1):59-63.
［2］张剑,吴青,羊昕旖,等. 基于条件随机场的农业命名实体识别［J］. 计算机与现代化, 2018(1):123-126.
［3］ Kalchbrenner N, Grefenstette E, Blunsom P. A convolutional neural network for modelling sentences［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguisties. 2014:655-665.〖HJ1.4mm〗
［4］ Yin Wenpeng, Schütze H. Convolutional neural network for paraphrase identification［C］// Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015:901-911.
［5］ Zhang Ye, Wallace B C. A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification［DB/OL］.https://arxiv.org/pdf/1510.03820v4.pdf, 2016-04-06.
［6］ Sun Shichang, Liu Hongbo, Lin Hongfei, et al. Twitter part-of-speech tagging using pre-classification hidden Markov model［C］// Proceedings of the 2012 IEEE International Conference on Systems, Man, and Cybernetics. 2012:1118-1123.
［7］ Mikolov T, Sutskever I, Chen Kai, et al. Distributed representations of words and phrases and their compositionality［C］// Proceedings of the 2013 International Conference on Neural Information Processing Systems. 2013:3111-3119.
［8］ Zhiyuli A, Liang Xun, Xu Zhiming. Learning distributed representations for large-scale dynamic social networks［C］// Proceedings of the 2017 IEEE Conference on Computer Communications. 2017, doi: 10.1109/INFOCOM. 2017.8057104.
［9］ Mikolov T, Chen Kai, Corrado G, et al. Efficient Estimation of Word Representations in Vector Space［DB/OL］.https://arxiv.org/pdf/1301.3781v3.pdf, 2013-09-07.
［10］Rong Xin. Word2vec Parameter Learning Explained［DB/OL］. https://arxiv.org/pdf/1411.2738v4.pdf, 2016-06-05.
［11］Goldberg Y, Levy O. Word2vec Explained: Deriving Mikolov et al.’s Negative-sampling Word-embedding method［DB/OL］. https://arxiv.org/pdf/1402.3722v1.pdf, 2014-02-15.
［12］Kim Y. Convolutional neural networks for sentence classification［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014:1746-1751.
［13］Oyama Y, Nomura A, Sato I, et al. Predicting statistics of asynchronous SGD parameters for a large-scale distributed deep learning system on GPU supercomputers［C］// Proceedings of the 2016 IEEE International Conference on Big Data. 2016:66-75.
［14］Zeiler M D, Taylor G W, Fergus R. Adaptive deconvolutional networks for mid and high level feature learning［C］// Proceedings of the 2011 International Conference on Computer Vision. 2011:2018-2025.
［15］Hinton G E, Srivastava N, Krizhevsky A, et al. Improving Neural Networks by Preventing Co-adaptation of Feature Detectors［DB/OL］. https://arxiv.org/pdf/1207.0580v1.pdf, 2012-07-03.
［16］Kone〖XCC2.TIF〗ny J, Liu Jie, Richtárik P, et al. Mini-batch semi-stochastic gradient descent in the proximal setting［J］. IEEE Journal of Selected Topics in Signal Processing, 2016,10(2):242-255.
［17］黄卫春,范少帅,熊李艳,等. 基于特征选择的人物关系抽取方法［J］. 科学技术与工程, 2015,15(3):254-259.

[1]	何思达, 陈平华. 基于意图的轻量级自注意力序列推荐模型[J]. 计算机与现代化, 2024, 0(12): 1-9.
[2]	黄庭培1, 马禄彪1, 李世宝2, 刘建航1. 基于WiFi和原型网络的手势识别方法[J]. 计算机与现代化, 2024, 0(12): 34-39.
[3]	张晓东1, 白广芝1, 李敏1, 李昊洋2. 基于经验小波变换的油气井产量预测模型 [J]. 计算机与现代化, 2024, 0(12): 53-58.
[4]	刘宝宝, 杨菁菁, 陶露, 王贺应. 基于注意力的DSMSC的遥感图像场景分类[J]. 计算机与现代化, 2024, 0(12): 72-77.
[5]	龚谊承1, 2, 刘青1, 2. 基于RF-LCE-BiLSTM-Attention-AMSSA模型的京剧二分类[J]. 计算机与现代化, 2024, 0(11): 7-12.
[6]	王莹莹, 郝潇. 基于Res2Net和递归门控卷积的细粒度图像分类[J]. 计算机与现代化, 2024, 0(10): 74-79.
[7]	焦一凯1, 2, 朱欣娟1, 2. 公共文化资源标签推荐方法[J]. 计算机与现代化, 2024, 0(10): 107-112.
[8]	周传华1, 2, 任太娇1, 罗岚1, 周昊1. 基于联合熵的非平衡数据边界混合重采样[J]. 计算机与现代化, 2024, 0(09): 95-100.
[9]	陈雪松1, 李衡1, 王浩畅2. 结合注意力机制和Mengzi模型的短文本分类[J]. 计算机与现代化, 2024, 0(09): 101-106.
[10]	何若男1, 范翔2, 陈益1, 姜羽菲1, 曹辉1. 比例优势逻辑回归优化嗓音障碍指数算法[J]. 计算机与现代化, 2024, 0(08): 1-4.
[11]	赵小明, 潘婷, 刘伟锋. 基于图像分类的自动绘画心理分析方法[J]. 计算机与现代化, 2024, 0(08): 92-97.
[12]	高帅鹏, 王怡凡. 基于图像的群体情绪识别综述[J]. 计算机与现代化, 2024, 0(08): 98-107.
[13]	周宪溪, 牟莉. 基于改进TF-IDF和AGLCNN的新闻长文本分类模型[J]. 计算机与现代化, 2024, 0(08): 120-126.
[14]	杨江1, 孙晓梅1, 许韬2. 基于业务内容构建股票关联关系的股价预测[J]. 计算机与现代化, 2024, 0(07): 21-25.
[15]	刘存莉1, 雷占占2, 郑澳2. 基于循环卷积神经网络的排水管网缺陷检测方法[J]. 计算机与现代化, 2024, 0(07): 26-35.

基于卷积神经网络的中文人物关系抽取方法

Chinese Personal Relation Extraction Method Based on Convolutional Neural Network

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