Event-Based Text Similarity Computing

Abstract

A large amount of research results have shown that events exist in many texts. Understanding texts from semantics, texts are composed of events, and events are the basic semantic units for texts. We present a novel approach for computing text similarity, which selects events as the features for documents and computes text similarity from two points of view: event class and event instance. The number of events is usually much fewer than the number of key words in documents. From this side, extracting event characters from documents is a good attempt to solve the high dimension of documents.