基于内容分析的网络新闻中社会网络自动抽取

本文针对网络新闻报道,提出了一种基于文本内容分析的社会网络自动抽取方法。此方法在对输入文章进行分词标注、共指消解等预处理之后，通过名词合并及主动词识别，得到存在关系的命名实体之间的关系指向和关系描述，最后通过有向图把存在关系的命名实体进行连接，形成由命名实体、实体间关系指向、实体间关系描述构成的关系网络。试验结果表明该方法对新闻中的命名实体关系抽取比较有效。

Extracting Social Network from Chinese News Stories by Content Analysis

Social networks have recently attracted much attention for their importance to the Semantic Web. Several methods exist to extract social networks for people from the web based on co-occurrence information. This paper proposed a content analysis based method for automatic obtaining social networks among various entities from Chinese event-based news stories. First, the input articles are annotated by lexical analysis. Second, the relationships among all entities are extracted by the way of main verbs recognition. For directed graph expression, an arrow is drawn between each pair of entities which have relationship from the agent argument to the patient one. Finally, all relationship expressions were established to build the social network up. Experiment results for relationships extraction indicate that our method can work well.