|Title:||The Automatic Summarization of the Scientific and Technical Texts; Linguistic and Computational Aspects: Realization of a prototype proceeding by extraction of sentences of the source text - RAFI- (Automatic Summarization by Indicating Fragments)||Add Dissertation|
|Author:||Abderrafih Lehmam||Update Dissertation|
|Institution:||University of Nancy 2, Department of Applied Linguistics|
|Linguistic Subfield(s):||Computational Linguistics;|
|Abstract:||The automatic text summary concerns the language industries. This work proposes a system automatically and directly transforming a source text into a reduced target text. The system deals exclusively with scientific and technical texts. It is based on the identification of specific expressions allowing an evaluation of the relevance of the sentence concerned, which can then be selected for the elaboration of the summary. The procedure consists in attributing a score to each sentence of the text and then eliminating those having the lowest scores. To produce the RAFI system ('Risumi Automatique ` Fragments Indicateurs' Automatic Summary based on Discourse Indicative Fragments), we resorted to the linguistic means of discourse analysis and the computing capacity of data processing instruments. This system would be adapted to the search tools of Internet or intranets.
See results of this research here : http://www.pertinence.net