Indic Script Corpus

1
Indic Script Corpus

• Ramachandra Budihal
• Mahabharata Samshodhana Pratisthanam
• Bangalore

2
Introduction

• India has the largest collection of Manuscripts
  in the World
• When harnessed would become the biggest
  traditional knowledge repository of the World
• Largest set of scripts gt 100
• More than 200 languages
• More than 20 odd materials of writing

3
The Challenge

• Putting this vast resource into a form that can
  enhance learning and scholarship
• To decipher the ancient scripts
• To promulgate the research and development such
  that the contents can reach the subject experts
• Tackle the dwindling no. of people who are
  knowledgeable on ancient scripts
• Capacity building exercise

4
The Mission

• To Digitize the collections
• To Document, Index and search
• To collate info from similar mss
• To transcribe from ancient script to modern
  script
• To critically analyze and edit the right text
  from the group
• To make the e-text corpus available to scholars
  and subject experts for furthering the knowledge
• To bring the ancient lost knowledge into the
  mainstream and bridge the digital divide of Indic
  Knowledge systems with contemporary systems

5
Complementary projects

• President of India has expressed his desire to
  complete the first four steps in next four years
• National Digital Manuscripts Library
• Digital Library of India

6
Technical details

• Mostly scripts are independent of Languages
• Most of the ancient texts in India belong to
  classical languages such as Sanskrit, Prakrit,
  Tamil etc.,
• Niche scripts belong to vernacular and some
  extinct regional languages

7
Technical Details

• This project is primarily a Proof of Concept
  (PoC)
• The target languages are Sanskrit, Tamil, Telugu
  and Kannada
• Targeted scripts are ancient and contemporary
  scripts that are prevalent in Manuscripts

8
Technical Details

• Refer Map

9
Thank you