Extracting Arabic proper nouns to avoid ambiguity

العناوين الأخرى

استخلاص أسماء العلم العربية لتجنب الغموض

مقدم أطروحة جامعية

Farhan, Muhammad Musa

مشرف أطروحة جامعية

Kanan, Ghassan

أعضاء اللجنة

al-Mashayikhi, Akram M. O.
Kanan, Tariq

الجامعة

جامعة عمان العربية

الكلية

كلية العلوم الحاسوبية و المعلوماتية

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2016

الملخص الإنجليزي

Information retrieval systems are becoming necessary in our daily life, for example thinking about checking your email, so it is important to find solutions that are IR systems is facing.

Arabic language is one of most difficult languages for non-native speaker to learn, read and to understand, so there are important issues that should be solved, and one of these issues is the ambiguity, which means that some words have similar form but different meaning, and the reason for this ambiguity is the absence of diacritics, which are very helpful to handle this issue, by defining the correct pronunciation of the word and so we get the correct meaning of it.

In the world of the internet there are many Arabic documents that are searched by many users using available search engines that help them to retrieve correct documents, which satisfy their information need, so the correct handling of search engines with those electronic collections is very important in order to give users the right information.

In other languages like English for example, this problem does not exist, and also many methods have been developed and researches has been written that handle similar situations, but in the Arabic language, there is a very poor number of researches, that have been published, which handle the issue of ambiguity of Arabic words that would help get better results.

The process of retrieving information from a collection of documents is very old and started since human beings began to think of how to archive related data together, which help them by finding specific documents quickly and easily, this core of retrieving information is still available nowadays.

So researchers have realized that the correct diacritics over the Arabic letters is very important, and still they need much research to learn how to deal with these diacritics, some of these researches have focused on Arabic verbs, but few of them have discussed the issue of handling diacritics with Nouns specially proper nouns.

Retrieving the correct information and serving them to the user is the Heart of every successful retrieval process, and in the Arabic language this is very difficult because of the absence of diacritics in most of the Arabic articles and books that cause some results that could be incorrect and irrelevant to the user, in this area there is very limited specially in the field of retrieving proper nouns from documents, that have the correct meaning, and since the invention of Computers, internet and the social media, that are used by many users in the Arabic world, it has become necessary to develop methods to be applied on these large amounts of electronic collections and documents.

Our thesis is going to discuss the issue of dealing with diacritics over Arabic letters and how to develop a system that is able to deal with these diacritics, especially diacritics over proper noun letters, as well as how they affect the meaning of words, in order this to get better Results.

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

عدد الصفحات

153

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-722915