Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExpert Neural System to parse Arabic Language
منظومة عصبونية خبيرة لإعراب اللغة العربية
767
0 42
0
(
0
)
Authors
محمد فاضل سكر( باحث )
Created by
Shamra Editor
Ask ChatGPT about the research
جرى تصميم منظومة عصبونية ذكية تعمل بمساعدة نظام خبير لبيان نحو و إعراب اللغة العربية. و جرت دراسة و تحليل أشكال الجمل العربية و أنواعها، و صنفت في حقول نحوية جديدة. يتكون كل حقل من العناصر الأساسية للجملة، من فعل و فاعل و مبتدأ و سواها. جرى إحصاء جميع الأشكال التي ترد عليها الجملة العربية، وُ فصلت في حقول فعلية و اسمية. جرى تصميم شبكة عصبونية تأخذ في مداخلها عناصر الجملة و تعطي في مخارجها الحقل النحوي المناسب.
New intelligent neural network built in an expert system has been designed to parse Arabic Language. Arabic sentences have been studied and analyzed, also classified into new syntactical fields. Each syntactical field consists of essential sentence components; verb, object, ….All emerging Arabic sentences have been calculated and detailed into verbal and noun fields.
References used
Grichnik Anthony, 2003, Artificial Intelligence, Strategy & Technolo- - gy Manager Caterpillar Inc
Holstvej.H.J., 2003, Visual Prolog version 6.1. Prolog Development Center A\S, Denmark
Kurfess Franz J, 2002, Knowledge-Based Systems, Computer Science Department Cal Poly
rate research
Read More
An expert system was developed to consider words' grammar case in Arabic phrases without diacritics. First, the system gets words' morphology and tags using Microsoft tool (ATK), then it depends on Arabic grammar to get words' grammar case in nominal
phrases. The system gave a very good results as they compared with Arabic language expert.
The emergence of Multi-task learning (MTL)models in recent years has helped push thestate of the art in Natural Language Un-derstanding (NLU). We strongly believe thatmany NLU problems in Arabic are especiallypoised to reap the benefits of such model
s. Tothis end we propose the Arabic Language Un-derstanding Evaluation Benchmark (ALUE),based on 8 carefully selected and previouslypublished tasks. For five of these, we providenew privately held evaluation datasets to en-sure the fairness and validity of our benchmark.We also provide a diagnostic dataset to helpresearchers probe the inner workings of theirmodels.Our initial experiments show thatMTL models outperform their singly trainedcounterparts on most tasks. But in order to en-tice participation from the wider community,we stick to publishing singly trained baselinesonly. Nonetheless, our analysis reveals thatthere is plenty of room for improvement inArabic NLU. We hope that ALUE will playa part in helping our community realize someof these improvements. Interested researchersare invited to submit their results to our online,and publicly accessible leaderboard.
تحتل الدراسات التي تتناول حوسبة اللغة العربية أهمية كبيرة نظراً للانتشار الواسع للغة العربية , و اخترنا في هذه الدراسة العمل على معالجة اللغة العربية من خلال نظام استرجاع معلومات للمستندات باللغة العربية , الفكرة الأساسية لهذا النظام هو تحليل المستن
دات والنصوص العربية و إنشاء فهارس للمصطلحات الواردة فيها , ومن ثم استخلاص أشعة أوزان تعبر عن هذه المستندات من أجل المعالجة اللاحقة للاستعلام و المقارنة مع هذه الأشعة للحصول على المستندات الموافقة لهذا الاستعلام .
من خلال عملية تجريد للمصطلحات الواردة في المستندات تم الحصول على كفاءة استرجاع أفضل , و تعرضنا للعديد من خوارزميات التجريد التي وصلت إليها الدراسات السابقة .
و تأتي عملية عنقدة المستندات كإضافة هامة , حيث يتمكن المستخدم من معرفة المستندات المشابهة لنتيجة البحث و التي لها صلة بـالاستعلام المدخل .
في التطبيق العملي , تم العمل على نظام استرجاع معلومات مكتبي , يقوم بقراءة نصوص ذات أنواع مختلفة و عرض النتائج مع العناقيد الموافقة لها .
Arabic and Ugaritic languages both belong to one linguistic
origin, and are connected with similar relations that came to both from
the Proto Semitic.
The linguistic materials are precisely read from the Ugarit texts
in order to extract all joint
or non-joint features. The comparisons and
their counters in Arabic languages will be in the light of the other Semitic
languages such as Phoenician-Canaanite, Hebrew, Syriac, and Akkadian
languages.
And since the letter “M” is a linguistic sound, which plays in
other languages ( rather than Arabic) the role that letter “N” plays
grammatically in Arabic language like dual ,normal, phonetic alterations,
and in structuring verbs, names, articles and pronouns.
Such comparative linguistic study between the two languages is
indicative dictionaric and phonetic comparisons, Moreover, it is a
continuation of the old origins of phonetic structures of pronunciation in
Arabic Language, a rejection of the indicative alternations and an
extraction of the phonetic laws that control the linguistic materials which
are under those linguistic comparisons.
Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a datas
et that is not biased by topic, dialect, or target. We produce the largest Arabic dataset to date with special tags for vulgarity and hate speech. We thoroughly analyze the dataset to determine which topics, dialects, and gender are most associated with offensive tweets and how Arabic speakers useoffensive language. Lastly, we conduct many experiments to produce strong results (F1 =83.2) on the dataset using SOTA techniques.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
