Entity Relation Eztraction to Free Tezt
A novel approach of the entity relation exaction proposed by this paper, it is different from the previous approaches, and the syntactic knowledge exaction specific section, which automatically extracts the characteristic words and patterns based on hierarchy bootstrapping machine learning. It advocates using a small amount of seed information and a large collection easily-obtained unlabeled data. Hierarchy bootstrapping makes use of seed words and seed patterns to build learning program, which extracts more characteristic words using Scalar Clusters. These characteristic words have semantic similarity with seed words. Then more extraction patterns could be learned automatically and added to the knowledge Base, moreover, we also pay attention to semantic and pragmatic knowledge for entity relation extraction. Moreover, the evaluation way belongs to the MUC. According to our experimental results, we can find it is useful method.
Entity Relation Ezaction Information Ezaction Bootstrapping Pragmatic Information
Suxiang ZHANG
Department of Electronic and Communication Engineering of North China Electric Power University, 071003 Baoding, China
国际会议
大连
英文
1-5
2009-09-24（万方平台首次上网日期，不代表论文的发表时间）