Automatic document summarization is a highly interdisciplinary research area related with computer science, multimedia, statistics, as well as cognitive psychology. In this paper, we introduce an intelligent system, the event indexing and summarization (EIS) system, for automatic document summarization, which is based on a cognitive psychology model (the event-indexing model) and the roles and importance of sentences and their syntax in document understanding. The EIS system involves syntactic analysis of sentences, clustering and indexing sentences with five indices from the event-indexing model, and extracting the most prominent content by lexical analysis at phrase and clause levels. After thorough implementation and objective evaluations, the system has shown good performance in multiple documents summarization. This system also incorporates special algorithms related with the third person pronoun resolution to extract the true entities that each sentence describes. © 2004 Elsevier Inc. All rights reserved.
- Automatic document summarization
- Clustering and indexing
- Lexical analysis
- Syntactic analysis