header
Local cover image
Local cover image
Image from OpenLibrary

A multi - layered system for arabic text diacritization / Aya Salah Metwally Hussein ; Supervised Amir F. Atiya , Mohsen A. Rashwan

By: Contributor(s): Material type: TextTextLanguage: English Publication details: Cairo : Aya Salah Metwally Hussein , 2015Description: 70 P. : plans ; 30cmOther title:
  • نظام متعدد الطبقات للتشكيل الالكترونى للنصوص العربية [Added title page title]
Subject(s): Online resources: Available additional physical forms:
  • Issued also as CD
Dissertation note: Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering Summary: In this work, we handle the problem of Arabic text diacritization. We propose a system of three layers in which every layer takes a step towards the full diacritization of the input sequence. We achieve very high WER in both morphological and syntactic diacritization. Our syntactic WER is 8.18% which is 4.9% better than the best published results. In addition, our system provides high speed processing which makes it very suitable for real time operations
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Home library Call number Copy number Status Barcode
Thesis Thesis قاعة الرسائل الجامعية - الدور الاول المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2015.Ay.M (Browse shelf(Opens below)) Not for loan 01010110067349000
CD - Rom CD - Rom مخـــزن الرســائل الجـــامعية - البدروم المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2015.Ay.M (Browse shelf(Opens below)) 67349.CD Not for loan 01020110067349000

Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering

In this work, we handle the problem of Arabic text diacritization. We propose a system of three layers in which every layer takes a step towards the full diacritization of the input sequence. We achieve very high WER in both morphological and syntactic diacritization. Our syntactic WER is 8.18% which is 4.9% better than the best published results. In addition, our system provides high speed processing which makes it very suitable for real time operations

Issued also as CD

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer

Local cover image