摘要: 为更全面准确地从字词搭配中获取语义搭配信息,提出一种新的语义搭配知识提取模型和知识库的表示方法。利用特殊度度量词语搭配的相关程度,在此基础上,基于知网的语义信息,实现从42万条记录的词语搭配中定量地抽取语义搭配信息。实验结果表明,该方法的语义搭配准确率为92.1%,且较大地扩充了字词搭配的规模。
关键词:
词语搭配,
语义搭配,
特殊度,
知识获取,
知识表示,
搭配知识库
Abstract: In order to achieve semantic collocation from word collocation, this paper proposes a new model of extracting semantic collocation and a new representation method of semantic collocation. By introducing Special Degree(SD) as a tool and utilizing knowledge of the HowNet, 420 000 records of words collocation are converted to semantic collocation in a quantitative way. Experimental results show that the accuracy of semantic collocation reaches 92.1%, and the semantic collocation expands the scale of the words collocation effectively.
Key words:
word collocation,
semantic collocation,
Special Degree(SD),
knowledge acquisition,
knowledge representation,
collocation knowledgebase
中图分类号:
王璐, 张仰森, 吴林. 基于多知识源的语义搭配知识获取及表示方法[J]. 计算机工程, 2012, 38(20): 109-112.
WANG Lu, ZHANG Ang-Sen, TUN Lin. Acquisition and Representation Method of Semantic Collocation Knowledge Based on Multiple Knowledge Sources[J]. Computer Engineering, 2012, 38(20): 109-112.