Information-content based sentence extraction for text summarization

Abstract

We propose the FULL-COVERAGE summarizer: an efficient, information retrieval oriented method to extract nonredundant sentences from text for summarization purposes. Our method leverages existing information retrieval technology by extracting key-sentences on the premise that the relevance of a sentence is proportional to its similarity to the whole document. We show that our method can produce sentence-based summaries that are up to 78% smaller than the original text with only 3% loss in retrieval performance.