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Sem Eval-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Sem Eval-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.
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.
作者
张春祥
赵凌云
高雪瑶
ZHANG Chun-xiang;ZHAO Ling-yun;GAO Xue-yao(School of Software and Microelectronics,Harbin University of Science and Technology,Harbin150080,China;School of Computer Science and Technology,Harbin University of Science and Technology,Harbin150080,China)
出处
《北京邮电大学学报》
EI
CAS
CSCD
北大核心
2019年第3期114-119,共6页
Journal of Beijing University of Posts and Telecommunications
基金
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)
关键词
词义消歧
卷积神经网络
消歧特征
语义类别
word sense disambiguation
convolution neural network
disambiguation features
semantic categories
