基于引文耦合分析方法的相关词识别.PDFVIP

第33卷摇 第7期 情摇 报摇 杂摇 志 Vol.33摇 No.7 2014年7月 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 JOURNAL OF INTELLIGENCE摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 July 摇 2014 基于引文耦合分析方法的相关词识别* 殷希红摇 乔晓东摇 张运良 (中国科学技术信息研究所摇 北京摇 100038) 摘摇 要摇 借鉴引文耦合分析方法,将词条定义中的实词比作词条的参考文献,根据词条定义中实词耦合强度实现相 关词的识别。 首先对词条定义进行分词和词性标注,并进行人工校对,然后抽取出动词和名词词性的实词,以词条 定义中实词的耦合强度作为判定标准实现相关词的推荐,并用人工校对的方法,计算相关词识别的准确率、召回率 和F值,论证该方法的有效性。 该实验将新能源汽车领域汉语科技词系统中随机选择的500 条词条及其定义作为 测试集,发现该方法可以达到较高的准确率和召回率。 关键词摇 词条定义摇 引文耦合分析摇 实词耦合摇 耦合强度摇 可视化 中图分类号摇 TP391摇 摇 摇 摇 摇 摇 文献标识码摇 A摇 摇 摇 摇 摇 文章编号摇 1002-1965(2014)07-0161-04 DOI摇 10.3969/j.issn.1002-1965.2014.07.029 Relevance Terms Recognition Based on Bibliographic Coupling Analysis Method Yin Xihong摇 Qiao Xiaodong摇 Zhang Yunliang (Institute of Scientific and Technical Information of China,Beijing摇 100038) Abstract摇 Enlightened by citation coupling analysis method,regarding the content words in the definition of term as the term爷s refer鄄 ences,according to the content wordscoupling strength of the term爷s definition,the relevance terms recognition is achieved. First,the Chinese word segmentation,part-of-speech tagging and manual correction of term definition areprocessed. Then,verbsand nounscon鄄 tentwordsareextractedandcontentwordscoupling strengthisregardedasthecriteriontoachievetherelevancetermsrecognition. Atlast, manual correction isused to calculate the precision andrecall ofrelevancetermsrecognition to demonstratethe effectivenessof thismeth鄄 od. Thisexperiment regardsthe Chinese scientific and technical vocabulary system爷s500 randomly selected termsand their definitionsas the test set (in the field of new energy vehicles) and find that the method can achieve a high precision and recall. Key words摇 term definition摇 b