Bridging the gap between Sanskrit Computational Linguistics tools and management of Sanskrit Digital Libraries


Venue : IIT-BHU
Date : Dec. 18th 2016

About

Program Committee

  • Pawan Goyal, IIT Kharagpur
  • Oliver Hellwig, Germany
  • Gérard Huet, Inria, Paris
  • Amba Kulkarni, IIAS, Shimla
  • Malhar Kulkarni, IIT Bombay
  • Dhaval Patel, Gujarat
  • Peter Scharf, Sanskrit Library, USA
  • Rajaram Shukla, BHU, Varanasi
  • Lalit Kumar Tripathi, RSkS, Allahabad
  • Srinivas Varakhedi, KSU, Bangalore

Several platforms of computational linguistics have been developed for Sanskrit. There are in-house efforts to use these computational linguistic tools for semi-automatic annotation of the Sanskrit corpus at various levels such as annotation of inflectional and derivational morphology, annotation of kāraka roles, and linking the stems with various digital lexica. These tasks are being carried out mostly semi-automatically involving a human supervision, or with a user interface for appropriate selection. Several Digital Sanskrit libraries are being developed. However, there is no present consensus on interoperability between the ones and the others, such as inter-translatable annotation of corpus. Moreover, for want of a common platform, there is very little communication among the researchers involved in the digital libraries and the computational linguists.

Objective

The goal of this workshop is to provide a forum for the various researchers involved in such efforts, in view of increasing cooperation in this area. The workshop would welcome participants both from the computational linguistics side and from the philology side, as well as traditional pandits interested in computer usage. This forum would provide a platform to discuss on the interoperability between the two platforms, such as inter-translatable annotation of corpus, development of proper user interfaces etc. facilitating bridging the gap between the two efforts.

Programme

The program schedule can be found here

26/09

First Call for Papers:
26th September

06/11

Submission Deadline:
Nov. 6th (Extended)

20/11

Acceptance Notification:
Nov. 20th

18/12

Workshop:
Dec. 18th

Accepted Papers

Call for Participation

The workshop invites submission in the following workshop topics.

  • Corpus Management
    • Sanskrit digital libraries formats
    • Versioning of digital libraries
    • Quality control of corpus acquisition, traceability of annotation
    • Incremental annotation and version control
    • Distribution and replication issues of digital libraries
  • Textual Representation
    • Format of metadata, line numbering
    • Lexical conventions concerning sandhi, avagraha, punctuation, quotations explicitation
    • Representation of ambiguities, śleṣa explicitation, notation for variants
    • Technical issues in computer encodings of Sanskrit
  • Annotations
    • Morphological tags for Sanskrit
    • Semantic roles tagging (kāraka/ākāṅkṣā)
    • Annotation training
    • Discourse tagging, anaphoric references explicitation
    • Meter recognition
    Statistical methods for annotation automation.
  • Digital Lexicon
    • Alignment of digital lexicons
    • Root concordances / Dhātupātha formalisation

Registration:


The workshop accepts submission of the following types

  • Regular papers (6-8 pages)
  • System Demonstrations (2-3 pages)

Submission Instructions:

  • The papers should be written either in English or in Sanskrit. Papers written in any other language will be rejected without any review. The authors must submit their papers before the deadline (1st November, anywhere in the world) by sending an email to icon2016workshop@gmail.com.
  • For demonstration papers, the authors are advised to give a link to their system, if accessible online, or provide some snapshots as appendix. Authors can use any number of pages for this appendix.

Invited Speakers

Organizing Committee