Center for Research in
Urdu Language Processing

 
 


 

 

 

National University of Computer & Emerging Sciences
FAST-NUCES


 
 

[ Projects ] [ Publications ] [ Activities ]

 
   
  Current Projects  
 

[ Current Projects ] [ Previous Projects ]

 
     
 

The Center for Research in Urdu Language Processing (CRULP) is first of its kind in Pakistan. The Center’s main objective is to conduct research for the evolution of computational models of Urdu and Pakistan’s other regional languages. The research at CRULP is carried within the context of projects, each having a well defined list of deliverables. Current projects being conducted at CRULP are:

 
  PAN Localization Project  
 

This project is an initiative of International Development Research Center (IDRC), Canada and the Center for Research in Urdu Language Processing (CRULP). The Objective of this project is to build local language computing capacity in regional institutions of Asia. Phase II of PAN Localization project will research into challenges associated with digital literacy of end-users using the localized technology for communication and to produce local language content. The project will also continue to further mature the language technology in the target languages. This project is led by researchers at CRULP, NUCES. CRULP will be coordinating efforts across Asia through ICT researchers, practitioners, linguists and policymakers from government agencies, universities and the private sector. The countries (and languages) included in the second phase of the project are Afghanistan (Pashto), Bangladesh (Bangla), Bhutan (Dzongkha), Cambodia (Khmer), China (Tibetan), Laos (Lao), Mongolia (Mongolian), Nepal (Nepali), Pakistan (Urdu) and Sri Lanka (Sinhala, Tamil).
PAN Localization Project

 
 

TOP

 
  PAN Localization Pakistan Component (Dareecha)  
 

This is the Pakistan Country Component of the PAN Localization Project. This project consists of three main activities:
1. Urdu localization of open source software
2. Developing training material and imparting ICT literacy training for using selected localized open source software and
3. Evaluation of the imparted ICT literacy training.

PAN Localization Pakistan Component

 
     
  Asian Language Support on Mobile Platform  
 

The project is researching to enable Asian languages on mobile platform. This minimally includes enabling complex Asian writing systems and input methods on this platform. Current mobile technology deploys bit map image based fonts for this purpose. However, over past few decades, it has been clearly learnt through the conventional computing that this is not the best and most effective way. Thus, have emerged the complex font formats, including the Open Type Fonts (OTF). Although OTF based fonts are now available for many complex Asian scripts, mobile platforms are not supporting them. This project aims to look into challenges of deploying open source rendering engine onto mobile platform, which would enable these existing complex fonts to be used.
Asian Language Support on Mobile Platform

 
     
  Microsoft Vista Urdu Language Interface Pack

TOP

 
 

The main objective of this project is to develop a Language Interface Package (LIP) for Microsoft Windows Vista and Microsoft Office . This language pack will provide Urdu language interface for Microsoft's upcoming Vista operating system. It will also enable the general masses  to use Microsoft Windows and Microsoft Office in Urdu language, who cannot understand English. For this purpose, the scope of the project includes translation of 300,000 English words in Urdu. Microsoft provides the translation tools (i.e. LocStudio) and translation files (i.e. *.edb). The translation is done at CRULP end. This project is sponsored by Microsoft Corporation, USA.
Microsoft Vista Urdu Language Interface Pack

 
     
  Adaptive English Language Teaching Tool  
 

The goal of this project is to develop a computer-aided language learning system for imparting English language skills to the students of class IX. Teaching materials and lessons will be developed in light of the aims and objective set out in the "National Curriculum of Pakistan", developed by the Ministry of Education. The project proposes to develop English Language Teaching Software and tools using a multi-modal interface with examples and illustrations which are relevant to our local and cultural setting. Also, to make this tool an effective medium of instruction, some of the examples and text will be in Urdu, which is a feature not present in most of the existing English language teaching software. This tool will be based on the state of the art techniques in artificial intelligence and human computer interface for intelligent user modeling and profiling.
The project is funded by National ICT R&D Fund and is being carried out in collaboration with NCA and IER.
Adaptive English Language Teaching Tool

 
   

TOP

 
  Telephone-based Speech Interfaces for Access to Information by Non-literate Users  
 

"Telephone-based Speech Interfaces for Access to Information by Non-literate Users” is a joint effort of CRULP in collaboration with the LTI department of Carnegie Mellon University and the Agha Khan University. The goal of this project is to investigate the use of speech interfaces in a field-deployed system by providing easy access to medical information to lady health workers in Pakistan. This will be achieved by developing a telephone based dialogue system consisting of an Urdu Speech Recognition system and a Text to Speech system that can interact with the health workers to answer their queries. However, a dialog system is much more than an ASR engine coupled with a TTS engine: a dialog system needs to be able to mimic human conversation abilities by providing an intuitive conversation flow, detecting and correcting recognition errors, and giving feedback to the caller throughout the call.

The Text-to-Speech system required for this project has already been developed by CRULP. In addition to the problems of ASR (Automatic Speech Recognition) that are still present for English, the prime impediment towards the completion of this project is the lack of research and local language resources for URDU. On an abstract level a speaker independent automatic continuous (and spontaneous) speech recognition system for local languages and its further adaptation to telephone based interface is required as a first step towards achieving this goal.
Telephone-based Speech Interfaces for Access to Information by Non-literate Users

 
   

TOP

 
  Punjab IT Labs Project Support  
 

This is a support project for easy usage of Urdu on the computer to facilitate end users in the Punjab IT Labs Project. The Punjab IT Labs projects by the Government of Punjab will be deploying IT labs in secondary schools of Punjab. Urdu language support will already be installed on the Microsoft platform in the labs, and CRULP will be providing some additional resources to improve the usability of Urdu on computers for new users.
Punjab IT Labs Project Support

 
     
 

TOP

 
 

webmaster@crulp.org