Extracting related named entities from blogosphere for event mining
Yoshihiko Suhara, Hiroyuki Toda, Akito Sakurai · 2008
We propose a method of extracting named entities that are related to a single input word. Focusing on the syntactic dependency relation in sentences, it is reasonable to extract a case element that syntactically depends on the predicate that the input word depends on. In Japanese, though, a word which has appeared in a previous sentence is often omitted or replaced. Our proposed method, first, extracts "predicate patterns" consisting of case elements with case particles and a predicate. Then it combines predicate patterns that have the same predicate to form possible unabridged dependence relations.