1998 · 74 citations · 11 references
ComputingComputer ScienceInformation RetrievalNatural Language ProcessingText AnalyticsInformation ExtractionText GenerationText PreprocessingText SummarizationDocument SummarizationDomain Knowledge ExtractionOne-pass AlgorithmsTemplate Filling
Text summarization is usually taken to mean producing a shorter version of an original document by retaining the most salient parts of the original text. Two approaches have been favored: selecting high contentbearing sentences influenced by positional constraints, and performing domain-dependent information extraction which fills a template from which a summary can be glossed. This paper presents a third approach to text reduction, producing shortened telegraphic versions of all input sentences. This approach shares the domain-independence advantage of the sentence selection and the one-pass advantage of information extraction template filling. We argue that this type of text reduction has some practical applications, and present the case of creating an audio scanner for the blind.
11
A trainable document summarizer
Julian Kupiec, Jan Pedersen, Francine Chen · 1995 · 1.3K citations · Full text
A practical part-of-speech tagger
Doug Cutting, Julian Kupiec, Jan Pedersen et al. · 1992 · 632 citations · Full text
An association thesaurus for information retrieval
Yufeng Jing, W. Bruce Croft · 1994 · 326 citations
SCISOR: extracting information from on-line news
Paul S. Jacobs, Lisa F. Rau · Communications of the ACM · 1990 · 217 citations · Full text
Computing, Computer Science, Finance +16