search

sebastianruder / NLP-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
https://nlpprogress.com/
MIT License
22.75k stars 3.62k forks source link

Arabic support for NLP-progress #244

Closed amrdarwish1975 closed 5 years ago

amrdarwish1975 commented 5 years ago

@sebastianruder What is the plan for Arabic support? As part of IBM Globalization team, part of our mission is to support Globalizing "open source".

NirantK commented 5 years ago

Hey @amrdarwish1975, what do you mean by Arabic support? A translation?

amrdarwish1975 commented 5 years ago

@NirantK By Arabic support I mean all Arabic enablement features (not translation) as follow: 1- Base Text Direction support: Mix between Arabic & English characters & process text to show the correct direction (whether RTL or LTR). 2- STructured Text support: Show the correct form of emails, file path, breadcrumb, date/timestamps & other structured text when mixing bet. English& Arabic 3- Process correct exported file formats like PDF, DOCX, ... etc for Arabic charcters. 4- National (Arabic-Indic) Digits & National (Hijri) Calendar support. 5- And more important from NLP dimension; processing Arabic language based on Arabic Grammar Rules & Language Modeling.

NirantK commented 5 years ago

@amrdarwish1975 This repo is dedicated to tracking research and progress of NLP.

A better place for Arabic NLP resources is at awesome-nlp. We already have a small and growing section for Arabic there

I am closing this issue here. Please feel free to open a new one at the awesome-nlp repo. I more than welcome a PR with your contributions along the points you mentioned.