ارسل ملاحظاتك

ارسل ملاحظاتك لنا







Minimum Redundancy And Maximum Relevance For Single And Multi Document Arabic Text Summarization

المصدر: مجلة جامعة الملك سعود - علوم الحاسب والمعلومات
الناشر: جامعة الملك سعود
المؤلف الرئيسي: Oufaida, Houda (Author)
مؤلفين آخرين: Nouali, Omar (Co-Author) , Blache, Philippe (Co-Author)
المجلد/العدد: مج26, ع4
محكمة: نعم
الدولة: السعودية
التاريخ الميلادي: 2014
الصفحات: 450 - 461
DOI: 10.33948/0584-026-004-010
ISSN: 1319-1578
رقم MD: 973382
نوع المحتوى: بحوث ومقالات
اللغة: الإنجليزية
قواعد المعلومات: science
مواضيع:
كلمات المؤلف المفتاحية:
Arabic Text Summarization | Sentence Extraction | Mrmr | Minimum Redundancy | Maximum Relevance
رابط المحتوى:
صورة الغلاف QR قانون
حفظ في:
المستخلص: Automatic text summarization aims to produce summaries for one or more texts using machine techniques. In this paper, we propose a novel statistical summarization system for Arabic texts. Our system uses a clustering algorithm and an adapted discriminant analysis method: mRMR (minimum redundancy and maximum relevance) to score terms. Through mRMR analysis, terms are ranked according to their discriminant and coverage power. Second, we propose a novel sentence extraction algorithm which selects sentences with top ranked terms and maximum diversity. Our system uses minimal language-dependant processing: sentence splitting, tokenization and root extraction. Experimental results on EASC and TAC 2011 Multi Lingual datasets showed that our proposed approach is competitive to the state of the art systems.

ISSN: 1319-1578

عناصر مشابهة