| |
| |
[ Projects ] [
Publications
] [
Activities
] |
|
| |
 |
|
| |
Previous Projects |
|
|
|
[
Current Projects ] [ Previous Projects ] |
|
| |
|
|
| |
The projects being previously done at
CRULP are:
|
|
| |
|
|
|
| |
Urdu
Localization Project |
|
|
| |
The Urdu localization
project envisages bringing the benefits of information
age to vast majority of Pakistan which are not literate
in English, the lingua franca of Internet, and thus are
deprived of the immense possibilities offered by this
revolution. It will also usher the Urdu language, the
national language of Pakistan spoken and understood by
masses, to the information age.
Urdu
Localization Project |
|
| |
|
|
| |
Urdu
Component Development |
|
| |
SpellChecker,
Collation and Normalization are basic language
utilities. The purpose of this project is to provide
APIs for these utilities for Urdu language. SpellChecker
utility will check words for spelling errors and will
suggest a ranked list of words if a spelling error is
found. Collation utility will provide a language
sensitive comparison of two strings with respect to
sorting. Normalization is a process to convert multiple
equivalent representations of data to consistent
underlying normal forms. |
|
| |
TOP |
|
| |
Lexicon for Urdu
Language |
|
| |
This project aims to develop a
lexicon for Urdu language for Nokia. This lexicon will
be used for future
development of speech and language technology. This
project includes the development of a lexicon of
commonly used words in Urdu, some domain specific words
and proper nouns.
The lexicon will also contain basic grammatical and
pronunciation information of these words, and will
provide almost complete corpus (and language) coverage.
The lexicon will be the fundamental building block for
other applications in script, speech and language
technologies, to be developed in the future, including
basic user services (e.g., SMS support, address book) to
more advanced user assistance applications (e.g.,
text-to-speech, speech recognition, spoken language
translation and handwriting recognition technologies).
Nokia has already indicated that follow-up work on Urdu
speech synthesis will be undertaken using this lexicon
(based on unit selection technique, which CRULP has not
yet done). This project is sponsored by Nokia Research, Beijing, China. |
|
| |
TOP |
|
| |
Sindhi English
Dictionary |
|
| |
The Sindhi English
Dictionary comprises of more than 2,000 words taken from
Mewaram Parmanand’s Sindhi-English Dictionary
(1866-1938, non-copyrighted), which presents Sindhi
words in the Sindhi-Arabic script. The word structure
for each Sindhi entry consists of variants, synonyms,
antonym, part of speech, inflections, grammatical
features and English senses. The digital dictionary for
Sindhi addresses research and pedagogical needs related
to the Sindhi language. It can be used as a basic
reference for scholars and students who want to access
Sindhi literature on the web. The Sindhi English
Dictionary project was supervised by Dr. Sarmad Hussain
at National University of Computer and Emerging
Sciences, Lahore, Pakistan. The project was developed in
collaboration with Dr. Jennifer Cole at University of
Illinois Urbana-Champaign and funded by South Asian
Language Resource Center (SALRC) at University of
Chicago. This dictionary can also be found at University
of Chicago website(http://dsal.uchicago.edu/dictionaries/mewaram/).
Home page of the Sindhi English Dictionary is
http://www.crulp.org/sed/ |
|
| |
TOP |
|
| |
Nafees Nastaleeq |
|
| |
Nafees Nasta’leeq
allows Urdu computing on Microsoft Windows 2000, NT, XP,
Unix and Linux platforms. This font enables desktop and
internet publishing, and electronic communication in
Urdu using existing software (without any plug-in)
supporting OTF specifications, e.g. MS Word, MS Excel,
MS Outlook (email), Internet Explorer, Netscape
Navigator, Mozilla and MS PowerPoint. This font is
developed according to calligraphic rules, following the
style of
Syed Nafees Al-Hussaini (Nafees Raqam), who is one
of the finest calligraphers of Pakistan. Guidance and
calligraphy of basic glyphs for the font has been
provided by Syed Jameel-ur-Rehman. He is the pupil of
Syed Nafees Shah and Hafiz Syed Anees-ul-Hassan. Nafees
Nasta’leeq OTF contains approximately 1,000 glyphs,
including about 26 ligatures. This font is operable on
all platforms supporting OTF specifications. This work
has been funded by Small Grants Program by IDRC, APDIP
UNDP and APNIC.
http://www.apdip.net/projects/ictrnd/2002/nafees/ |
|
| |
|
|
| |
Sindhi English
Dictionary |
|
| |
The Sindhi English
Dictionary comprises of more than 2,000 words taken from
Mewaram Parmanand’s Sindhi-English Dictionary
(1866-1938, non-copyrighted), which presents Sindhi
words in the Sindhi-Arabic script. The word structure
for each Sindhi entry consists of variants, synonyms,
antonym, part of speech, inflections, grammatical
features and English senses. The digital dictionary for
Sindhi addresses research and pedagogical needs related
to the Sindhi language. It can be used as a basic
reference for scholars and students who want to access
Sindhi literature on the web. The Sindhi English
Dictionary project was supervised by Dr. Sarmad Hussain
at National University of Computer and Emerging
Sciences, Lahore, Pakistan. The project was developed in
collaboration with Dr. Jennifer Cole at University of
Illinois Urbana-Champaign and funded by South Asian
Language Resource Center (SALRC) at University of
Chicago. This dictionary can also be found at University
of Chicago website(http://dsal.uchicago.edu/dictionaries/mewaram/).
Home page of the Sindhi English Dictionary is
http://www.crulp.org/sed/ |
|
| |
TOP |
|
|
|
