The First International Symposium on Sanskrit Computational Linguistics
Paris, France - This symposium will be followed by a workshop on standardization issues related to Sanskrit linguistic resources. Communications are solicited for the Symposium, and propositions of participation to the workshop will be considered as well.
First International Sanskrit Computational Linguistics Symposium
Paris, October 29-31, 2007
Context
The Rocquencourt Laboratory of INRIA (French National Institute for Informatics and Automatics) recently joined efforts with the Department of Sanskrit Studies at University of Hyderabad and the NLP Department of the Rashtriya Sanskrit Vidyapeetha at Tirupati, within a joint team in Sanskrit Computational Linguistics. The joint team will hold its first Workshop at the end of October 2007 in Paris.
Announcement
The First International Symposium on Sanskrit Computational Linguistics will take place in the Paris area on the 29th and 30th of October 2007, followed on the 31st by a workshop on standardization issues related to Sanskrit linguistic resources. Communications are solicited for the Symposium, and propositions of participation to the workshop will be considered as well.
Scope
Potential areas of interest are:
Representation of morpho-phonetics; encoding of phonological features and prosody; sandhi application and analysis; morphological paradigms and parameters for classical Sanskrit (both derivational and inflectional)
Representation of a Sanskrit Generative Lexicon; Sanskrit Wordnet; Sanskrit to pivot semantic formats
Sense disambiguation, treatment of ontological structure, proper nouns recognition in Sanskrit
Tagging and shallow syntax; dependency grammars for Sanskrit, kaaraka representation and processing
Representation of Sanskrit syntax; treebank formats for Sanskrit; Sanskrit parsing
Standardization, interoperability issues; evaluation of linguistic tasks such as tagging, stemming, parsing
Corpus tagging at various levels of granularity. Indexing and anchoring of citations. Prosody representation
Multi-layer corpus architecture for philology applications (manuscript variants, critical editions, commentary structure)
Computerization of Paninean descriptions, representation of suutras, vaarttikas, ga.napaa.thas, dhaatupaa.thas
