Arabic text summarization using dynamic template

العناوين الأخرى

تلخيص نص اللغة العربية باستخدام القوالب التفاعلية

مقدم أطروحة جامعية

Alawinah, Muhammad Sami N.

مشرف أطروحة جامعية

Nassar, Muhammad Uthman

الجامعة

جامعة عمان العربية

الكلية

كلية العلوم الحاسوبية و المعلوماتية

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2018

الملخص الإنجليزي

The online information available on World Wide Web is in enormous amount.

Search engines like Google, Yahoo were developed to retrieve information from the databases.

But actual results were not obtained as the electronic information is increasing day by day.

Thus automatic summarization came into demand.

Automatic summarization gathers several documents as input and provides the shorter summarized version as output which is informative, unambiguous, save valuable time.

Single document text summarization is one of the summarization type that has the ability to distinguish the most informative or the less informative portion of the text in one document.

This study is to propose a new mechanism for Arabic text summarization based on dynamic template to be applied in single document text.

The proposed mechanism is evaluated using CNN Arabic corpus.

Then, it compared with other existing mechanism (i.e.

Al-Zoubi’s mechanism) based on different evaluation metrics, including: text quality, non-redundancy, reference clarity, coherence, precision, recall, accuracy.

The results indicated that proposed mechanism is more efficient than Al-Zoubi’s mechanism.

In detail, the summary resulted from the proposed policy has very strong overall text quality level (4.775 out of 5), very strong overall non-redundancy level (4.84 out of 5), very strong overall reference clarity level (4.775 out of 5), very strong overall coherence level (4.775 out of 5).

In addition, it achieves very high level of accuracy (0.992), precision (0.98) and recall (0.96).

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الموضوعات

• الذكاء الاصطناعي
• اللسانيات الحاسوبية
• استرجاع المعلومات

عدد الصفحات

76

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-932642