Project background and justification
South Asia is one of those unique parts of the world where single
languages are written in different scripts. In India, Urdu is written
in the Devnagri script (left-to-right), while in Pakistan, it is
written in an Arabic-based Urdu script (right-to-left).
The problem of communication between Hindi and Urdu languages has long
been a social barrier between the Muslim and Hindu populations of India
and a key barrier to people-to-people contact between India and
Pakistan.
This project aims to bring the Urdu and Hindi speaking people closer by
developing a transliteration/translation tool for the two languages
that may help people link across a hostile geographical divide. In so
doing we will provide an ICT solution to a social problem that had
seemed insurmountable for centuries.
The option of a transliteration component is to enable the
well-developed poetic verse of the Urdu language to be available to the
Hindi literate public. The translation tool will enable conversion of
Urdu websites to Hindi and vice versa, enabling them to read in their
own languages. This will in turn facilitate electronic and written
communication between people living in India and Pakistan.
Project summary
Even
though over 600 million people in India and Pakistan speak Hindi and
Urdu, the languages are written in mutually incomprehensible scripts
despite sharing the same grammar and more than 70 per cent of commonly
used words.
After 12 years of academic research on the
development of languages and literacy in Pakistan and India, a tool has
been developed to facilitate electronic and written communication
between Indians and Pakistanis through the development of a
bi-directional web-based Hindi-Urdu Language
Transliteration/Translation Tool.
The main modules to be developed are:
• Urdu-Hindi electronic dictionary
• Transliteration/translation rules and mapping tables
• Parallel Hindi/Urdu Corpus
• Tool to convert any Unicode-based Hindi website to Urdu and reverse
The
target groups will be media organizations (such as
magazines/newspapers), literary and literacy promotional organizations,
writers, and NGOs involved in dissemination activity amongst the urban
and rural poor, and virtual Hindi-Urdu speaking communities, schools,
and colleges.
Organization profile
One of the premier public institutions of higher education in Northern
India, Punjabi University was established in 1962, with the highest
grading of A by the NAAC. Five departments and one research centre are
exclusively devoted to the development of various aspects of the
Punjabi language, literature and culture.
The Advanced Centre for the Technical development of the Punjabi
Language, Literature and Culture was established in February 2004, with
the aim of conducting research and development into the linguistic and
computational aspects of the Punjabi Language. The department has also
carved a niche in the area of transliteration and translation. It
developed, for the first time, an online Shahmukhi (Urdu) to Gurmukhi
transliteration tool and a Punjabi to Hindi translation system. Both
were demonstrated in the 22nd International conference on Computational
Linguistics held at Manchester, UK in August 2008.
More information about the Punjabi University at
http://www.punjabiuniversity.ac.in/