基于卷积神经网络的词义消歧

doi:10.13190/j.jbupt.2018-148

北京邮电大学学报 ›› 2019, Vol. 42 ›› Issue (3): 114-119.doi: 10.13190/j.jbupt.2018-148

基于卷积神经网络的词义消歧

张春祥¹, 赵凌云², 高雪瑶²

1. 哈尔滨理工大学软件与微电子学院, 哈尔滨 150080;
2. 哈尔滨理工大学计算机科学与技术学院, 哈尔滨 150080

收稿日期:2018-07-11 出版日期:2019-06-28 发布日期:2019-06-20
通讯作者: 高雪瑶(1979-),女,副教授,硕士生导师,E-mail:xueyao_gao@163.com. E-mail:xueyao_gao@163.com
作者简介:张春祥(1974-),男,教授,硕士生导师.
基金资助:
国家自然科学基金项目（61502124，60903082）；中国博士后科学基金项目（2014M560249）；黑龙江省普通高校基本科研业务费专项资金项目（LGYC2018JC014）；黑龙江省自然科学基金项目（F2015041，F201420）

Word Sense Disambiguation Based on Convolution Neural Network

ZHANG Chun-xiang¹, ZHAO Ling-yun², GAO Xue-yao²

1. School of Software and Microelectronics, Harbin University of Science and Technology, Harbin 150080, China;
2. School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China

Received:2018-07-11 Online:2019-06-28 Published:2019-06-20

摘要/Abstract

摘要： 为了提高词义消歧性能，提出了一种基于卷积神经网络的消歧方法.以歧义词为中心，向左右两侧连续扩展4个邻接词汇单元，选取其中的词形、词性和语义类作为消歧特征.以消歧特征为基础，使用卷积神经网络来确定歧义词的语义类别.利用SemEval-2007：Task#5的训练语料和哈尔滨工业大学语义标注语料来优化卷积神经网络.使用SemEval-2007：Task#5的测试语料来测试词义消歧分类器的性能，所提方法的消歧平均准确率有提高.实验结果表明，该方法在词义消歧中是可行的.

关键词: 词义消歧, 卷积神经网络, 消歧特征, 语义类别

Abstract: In order to improve the performance of word sense disambiguation (WSD), a disambiguation method based on convolution neural network (CNN) is proposed. Ambiguous word is viewed as center and four adjacent word units around its left and right sides are extended. Word, part-of-speech and semantic categories are extracted as disambiguation features. Based on disambiguation features, CNN is used to determine semantic categories of ambiguous words. Training corpus of SemEval-2007:Task#5 and semantic annotation corpus from Harbin Institute of Technology are used to optimize CNN classifier. Testing corpus of SemEval-2007:Task#5 is used to test the performance of WSD classifier. Average disambiguation accuracy of the proposed method is improved. Experiments show that this method is feasible in WSD.

Key words: word sense disambiguation, convolution neural network, disambiguation features, semantic categories

中图分类号:

TP391.2

张春祥, 赵凌云, 高雪瑶. 基于卷积神经网络的词义消歧[J]. 北京邮电大学学报, 2019, 42(3): 114-119.

ZHANG Chun-xiang, ZHAO Ling-yun, GAO Xue-yao. Word Sense Disambiguation Based on Convolution Neural Network[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2019, 42(3): 114-119.

参考文献

[1] 杨陟卓, 黄河燕.基于异构关系网络图的词义消歧研究[J].计算机研究与发展, 2013, 50(2):437-444.Yang Zhizhuo, Huang Heyan.WSD method based on heterogeneous relation graph[J].Journal of Computer Research & Development, 2013, 50(2):437-444.
[2] Koppula N, Rani B P, Rao K S.Graph based word sense disambiguation[C]//The 1^st International Conference on Computational Intelligence and Informatics.Hyderabad:Springer, 2017:665-670.
[3] Duque A, Martinezromo J, Araujo L.Can multilinguality improve biomedical word sense disambiguation?[J].Journal of Biomedical Informatics, 2016, 64(1):320-332.
[4] 杨安, 李素建, 李芸.基于领域知识和词向量的词义消歧方法[J].北京大学学报(自然科学版), 2017, 53(2):204-210.Yang An, Li Sujian, Li Yun.Word sense disambiguation based on domain knowledge and word vector model[J].Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(2):204-210.
[5] 李赟, 黄开妍, 任福继, 等.维基百科的中文语义相关词获取及相关度分析计算[J].北京邮电大学学报, 2009, 32(3):109-112.Li Yun, Huang Kaiyan, Ren Fuji, et al.Wikipedia based semantic related Chinese words exploring and relatedness computing[J].Journal of Beijing University of Posts and Telecommunications, 2009, 32(3):109-112.
[6] Faisal E, Nurifan F, Sarno R.Word sense disambiguation in Bahasa Indonesia using SVM[C]//The 3^rd International Seminar on Application for Technology of Information and Communication.Semarang:IEEE, 2018:239-243.
[7] 王桐, 王磊, 吴吉义, 等.WordNet中的综合概念语义相似度计算方法[J].北京邮电大学学报, 2013, 36(2):98-106.Wang Tong, Wang Lei, Wu Jiyi, et al.Semantic similarity calculation method of comprehensive concept in WordNet[J].Journal of Beijing University of Posts and Telecommunications, 2013, 36(2):98-106.
[8] 李源, 翟宏森, 刘凤娇, 等.汉语复句中基于依存关系与最大熵模型的词义消歧方法研究[J].计算机与数字工程, 2018, 46(1):78-82.Li Yuan, Zhai Hongsen, Liu Fengjiao, et al.Research on word sense disambiguation method based on dependency relation and maximum entropy in Chinese complex sentences[J].Computer & Digital Engineering, 2018, 46(1):78-82.
[9] 何径舟, 王厚峰.基于特征选择和最大熵模型的汉语词义消歧[J].软件学报, 2010, 21(6):1287-1295.He Jingzhou, Wang Houfeng.Chinese word sense disambiguation based on maximum entropy model with feature selection[J].Journal of Software, 2010, 21(6):1287-1295.
[10] Gutierrez Y, Vazquez S, Montoyo A.Spreading semantic information by word sense disambiguation[J].Knowledge-Based Systems, 2017, 132(1):47-61.
[11] Jimeno Y A.Word embeddings and recurrent neural networks based on long-short term memory nodes in supervised biomedical word sense disambiguation[J].Journal of Biomedical Informatics, 2017, 73(1):137-147.
[12] Huang Zhehuang, Chen Yidong.An improving SRL model with word sense information using an improved synergetic neural network model[J].Journal of Intelligent & Fuzzy Systems, 2016, 31(3):1469-1480.
[13] Tripodi R, Pelillo M.A game-theoretic approach to word sense disambiguation[J].Computational Linguistics, 2017, 43(1):31-70.
[14] Iacobacci I, Pilehvar M T, Navigli R.Embeddings for word sense disambiguation:an evaluation study[C]//The 54^th Annual Meeting of the Association for Computational Linguistics.Berlin:ACL, 2016:897-907.
[15] Kang M Y, Kim B, Lee J S.Word sense disambiguation using embedded word space[J].Journal of Computing Science and Engineering, 2017, 11(1):32-38.
[16] Zhan Jingwen, Chen Yanmin.Research of Chinese word sense disambiguation based on HowNet[C]//The 2011 International Conference on Artificial Intelligence and Computational Intelligence.Taiyuan:Springer, 2011:477-482.
[17] Hung C, Chen S J.Word sense disambiguation based sentiment lexicons for sentiment classification[J].Knowledge-Based Systems, 2016, 110(1):224-232.

基于卷积神经网络的词义消歧

Word Sense Disambiguation Based on Convolution Neural Network

PDF

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

[1]	余佳润王亚峰. 一种低信噪比下基于深度学习的DoA估计方法[J]. 北京邮电大学学报, 2022, 45(6): 119-125.
[2]	叶康张淑军郭淇李辉崔雪红. 基于CM-Transformer的连续手语识别[J]. 北京邮电大学学报, 2022, 45(5): 49-53,78.
[3]	武兴坤, 罗涛, 刘爱军, 杨明, 张文静. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[4]	武兴坤罗涛刘爱军杨明张文静李剑峰李文秀. 面向主动脉缩窄辅助诊断的神经网络模型设计[J]. 北京邮电大学学报, 2022, 45(4): 1-6.
[5]	许同乐, 孟良, 孔晓佳, 苏元浩, 孙砚飞. 基于EEMD的ICNN故障诊断方法[J]. 北京邮电大学学报, 2022, 45(2): 110-116.
[6]	李晓辉, 王先文, 樊韬, 刘佳文, 万宏杰. 基于卷积神经网络的高性能5G下行同步算法[J]. 北京邮电大学学报, 2022, 45(2): 117-123.
[7]	王靖, 姜竹青, 门爱东, 郭晓强, 王智康. 阶梯式图像去噪方法[J]. 北京邮电大学学报, 2022, 45(1): 52-57.
[8]	刘永利, 朱亚孟, 晁浩. 多策略MRFO算法的卷积神经网络超参数优化[J]. 北京邮电大学学报, 2021, 44(6): 83-88,95.
[9]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.
[10]	王艺霏, 莫爽, 吴文睿, 范少华, 肖丁. 基于内外卷积网络的网络入侵检测[J]. 北京邮电大学学报, 2021, 44(5): 94-100.
[11]	刘国桢, 陈鸿龙. 卷积记忆图协同过滤[J]. 北京邮电大学学报, 2021, 44(3): 21-26.
[12]	彭鹏, 李卓, 梁纪峰, 马天祥, 刘开华. 支持泛洪攻击检测的命名数据网PIT[J]. 北京邮电大学学报, 2021, 44(2): 61-67.
[13]	曹毅, 黄子龙, 盛永健, 刘晨, 费鸿博. D-2-DenseNet噪音鲁棒的城市音频分类模型[J]. 北京邮电大学学报, 2021, 44(1): 86-91.
[14]	蒲悦逸, 王文涵, 朱强, 陈朋朋. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9-14.
[15]	谢晓燕, 赵欢, 蒋林. 基于视频数据特性的动态手势识别[J]. 北京邮电大学学报, 2020, 43(5): 91-97.