Communication
among human beings is inherently multi-modal, visual and aural
modes being the primary modes. Currently, the principal means
of human machine communication is heavily biased towards the
convenience of the machine rather than that of man. Mouse
and keyboard are primary input devices and visual display
unit is the primary output device. Usage of such interfaces
requires special skills and mental attitude, which many people
are not endowed with. This machine-centric mode of communication
needs to be changed in favour of human-centric interfaces
so that all people share the benefit of the power of computers.
While visual mode is most effective in capturing information,
speech remains the preferred and most convenient means of
conveying information. The advantage of verbal communication
has become even stronger today due to convergence of computers
and telecommunication systems, which allows people to access
information on computers located remotely.
The verbal communication involves natural language,
and this brings to fore the role of linguistics in the information
technology. Therefore, human-centric interface to computer is the
need of the day. Human beings are endowed with a unique faculty-the
language-through which they share information, thoughts and ideas
effortlessly among themselves. Facilitating human machine interaction
using natural language involves several facets of human language
technology: speech compression, recognition and understanding of
speech and script, machine translation, text generation, synthesis
of speech and cursive script. Both forms of language, spoken and
written, are useful for interaction with machine.
Indian languages work on Computer is being carried
out for last two decades accomplishing variety of tasks, including
data processing, word processing, desktop publishing etc. on different
platforms and operating systems.
Department of Information Technology initiated
the TDIL (Technology Development for Indian Languages) programme
with the objective of developing Information Processing Tools and
Techniques to facilitate human-machine interaction without language
barrier; creating and accessing multilingual knowledge resources;
and integrating them to develop innovative user products and services.
Projects were funded to develop linguistic resources such as corpora
and dictionaries; and basic information processing tools such like
fonts, text editor, spell checker; OCR and Text-to-Speech. Standards
were also evolved.
Various efforts have been made at various places
in Private, Public and Government Level in the country to develop
Indian Language technology products and Services. Language Technologies
and tools developed by Resource Centres and Coilnet Centres need
to be brought fast to the use for feedback generation and made them
available for productizing. The research & development efforts
should have impact on society at large. It necessarily means that
the developmental efforts should not be restricted to the lab environment,
but these need to be deployed fast, which finally bring the users
feedback & experience for further refinement.
Government is all set to provide the following
products and solutions in public domain over the next one year:
-
Free fonts (TTF and OTF) and word processors
in all Indian languages. As a first step, popular True Type
Fonts (TTF) for the classical language Tamil have been selected
through interaction with publication industry for release in
public domain free of cost. TTF fonts are widely in use with
systems having Windows 95/ Windows 98/ Windows NT platform.
For systems with Windows 2000/XP/2003 and Linux platforms OTF
(Open type font) are being released. This effort is first of
its kind and most of the word processors (existing and new)
will be able to make use of these fonts. This in turn will make
more fonts available for users with Tamil Net/Tamil 99 and Typewriter
keyboards for data entry.
-
Optical Character recognition (OCR) in all
Indian languages for information extraction, retrieval and digitization.
OCR makes it possible to convert scanned image (printed page
scanned using scanner) to editable text so that it can be used
for other applications and can be modified accordingly. The
publishing industry is one of the major beneficiaries, who can
use this software to reproduce and bringing out the new editions.
-
Speech Interfaces for Systems such as Railway
Information, Healthcare, Agriculture, Disaster Management and
other public utility services. This will help people at large
to take benefits of advanced technologies in Indian Languages.
The interface with the system can use speech recognition engine
to recognize human voice and convert it to text for information
extraction. Text to speech can be used to read out text for
visually impaired persons for applications such as fetching
information from Internet.
-
Internet access tools for Indian languages
like Browsers, Search Engines and email. With these, sending
email in Indian languages will be possible and search engine
will provide facility to search information in other Indian
languages while giving query in one of the Indian languages.
-
On line translation services tools amongst
Indian languages and English. It will help people to translate
content in English & any Indian languages to target Indian
language of their choice.
The products/services are being made available
through TDIL Data Centre with online helpdesk.
Government has a mission and time bound activity
plan for TDIL-DC (Language Technology Utilities Distribution Channel)
to boost research, productization, deployment and support through
- Opening developed technologies to the market
- Upgrading or refining technologies to formulate products
- Developing need based new technologies
In order to achieve these, following steps actions
are being taken
-
Distribution of Indian languages technologies/tools
through TDIL Data
Centre in a phase wise manner
-
Acquisition of developed tools, technologies,
products and services
-
Spreading awareness and publicizing the
efforts of government in Language Technology areas through available
tools and technologies
-
Facilitating user for free downloads of
tools, utilities, products etc.
-
Promoting Public-Private partnership in
Language Technology
-
Launching missions of specific application
areas
|