CAJ | 학술논문

针对现有隐喻计算知识库的广度和深度不足问题，提出了引入了网络百科资源作为隐喻识别的世界知识库的方法.利用信息检索技术，从概念对应的百科页面中获取概念的背景世界知识，计算两个概念的世界知识的重合程度，作为判断它们是否属于同一个概念域的依据，进行隐喻的识别.实验结果表明在使用百度百科作为世界知识库时，隐喻/常规表达的识别正确率达到81.06%，算法的有效性得到证明.
침대현유은유계산지식고적엄도화심도불족문제，제출료인입료망락백과자원작위은유식별적세계지식고적방법.이용신식검색기술，종개념대응적백과혈면중획취개념적배경세계지식，계산량개개념적세계지식적중합정도，작위판단타문시부속우동일개개념역적의거，진행은유적식별.실험결과표명재사용백도백과작위세계지식고시，은유/상규표체적식별정학솔체도81.06%，산법적유효성득도증명.
Aim at the low coverage of current hand-coded knowledge base used in the metaphor recognition, a Chinese nominal metaphor recognition method based on exploiting the online encyclopedia resource is proposed. A noun is represented as a page in the encyclopedia. Capture the world knowledge from the page of encyclopedia, calculates the relatedness between the pages of the two nouns in the nominal reference by applying information retrieval methods. The relatedness determines the reference is metaphorical or not. The experimental results shows that the accuracy of metaphorical/normal references recognition can reach 81.06%by using BaiduBaike. It supports the validity, efficiency of this method.