Paper: A Scaleable Multi-Document Centroid-Based Summarizer

ACL ID N04-3007
Title A Scaleable Multi-Document Centroid-Based Summarizer
Venue Human Language Technologies
Session System Demonstration
Year 2004

This approach can produce good summaries but is usually knowledge intensive and domain dependent. Sentence extraction techniques (Luhn, 1958; Radev et al. , 2000), on the other hand, compute a score for each sentence based on certain features and output the most highly ranked sentences. This approach is conceptually straightforward and usually domain independent, but the summaries produced by it often need further revision to be more smooth and coherent. 1.2 Centroid-based summarization and MEAD Centroid-based summarization is a method of multidocument summarization. It operates on a cluster of documents with a common subject (the cluster may be produced by a Topic Detection and Tracking, or TDT, system). tem). A cluster centroid, a collection of the most important words from the whole clu...