Abstract Generation based on Rhetorical Structure Extraction

Simple item page
dc.creatorOno, Kenji
dc.creatorSumita, Kazuo
dc.creatorResearch, Seiji Miike
dc.creatorCenter, Development
dc.creator1, Toshiba Corporation Komukai-Toshiba-cho
dc.creatorSaiwai-ku
dc.creatorKawasaki
dc.creator210
dc.creatorJapan
dc.date1994-11-17
dc.date.accessioned2026-07-07T09:09:39Z
dc.date.available2026-07-07T09:09:39Z
dc.descriptionWe have developed an automatic abstract generation system for Japanese expository writings based on rhetorical structure extraction. The system first extracts the rhetorical structure, the compound of the rhetorical relations between sentences, and then cuts out less important parts in the extracted structure to generate an abstract of the desired length. Evaluation of the generated abstract showed that it contains at maximum 74\% of the most important sentences of the original text. The system is now utilized as a text browser for a prototypical interactive document retrieval system.
dc.description5 pages including 2 eps Figure, using epsbox.sty, art10.sty
dc.identifierhttps://arxiv.org/abs/cmp-lg/9411023
dc.identifierhttp://arxiv.org/abs/cmp-lg/9411023
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151114
dc.subjectComputation and Language
dc.titleAbstract Generation based on Rhetorical Structure Extraction
dc.typetext

Files

Collections

arXiv