Title :
Experimentation of Two Compression Strategies for Multi-document Summarization
Author :
Fatma, Jaoua Kallel ; Belguith, Lamia Hadrich ; Jaoua, Maher ; Hamadou, Abdelmajid Ben
Author_Institution :
MIRACL Lab., Higher Inst. of Manage. of Gabes, Gabes, Tunisia
Abstract :
In this paper, we compare two strategies for the integration of a compression module in the automatic summarization chain. The first strategy, that we call precompression uses sentence compression in the first stage of summarization by producing all reduced forms of original sentences. The second strategy, called post-compression, reduces extract´s sentences in order to generate the final extract. The experiment results are presented on a document set extracted from the DUC´04 evaluation conference.
Keywords :
document handling; automatic summarization chain; extract sentence reduction; multidocument summarization; post-compression; precompression; sentence compression; Conference management; Context modeling; Data mining; Dictionaries; Engineering management; Filtering; Hidden Markov models; Laboratories; Probability; automatic summarization; filtering; post-compression; pre-compression; sentence compression;
Conference_Titel :
Computer and Electrical Engineering, 2009. ICCEE '09. Second International Conference on
Conference_Location :
Dubai
Print_ISBN :
978-1-4244-5365-8
Electronic_ISBN :
978-0-7695-3925-6
DOI :
10.1109/ICCEE.2009.263
