Locality-Based pruning methods for web search
ACM Transactions on Information Systems (TOIS)
AdaSum: an adaptive model for summarization
Proceedings of the 17th ACM conference on Information and knowledge management
| Hi-index | 0.01 |
This paper proposes the FULL-COVERAGE summarizer:an efficient, information retrieval oriented method to extractnon-redundant sentences from text for summarization purposes.Our method leverages existing Information Retrievaltechnology by extracting key-sentences on the premise thatthe relevance of a sentence is proportional to its similarityto the whole document. We show that our method can producesentence-based summaries that are up to 78% smallerthan the original text with only 3% loss in retrieval performance.