Home Work Going On
PDF Print

Work Going On.....

  • e-Corpus Collection

      Generated an e-Corpus of 4,00,000 words.

  • Annotation

      Out of 4,00,000 words 1,80,000 words have been annotated using the ILMT POS guidelines.

  • Part-of-Speech(POS) Tagger

      Automatic POS tagger for Kashmiri is been developed and presently an accuracy of 80.6% is achieved.

  • Kashmiri e-Dictionary

    • Simple English-Kashmiri of 12,000 entries for role out CD (CDAC Pune Format).
    • Online Trilingual English-Kashmiri-Hindi Dictionary, presently containing 10,768 entries.
    • Synset Based Dictionary - Completed 10,00 synsets so far (Core Synsets + Common Synsets).

  • Kashmiri Morph Analyzer

    • Rule based approach is followed in consultation with IIT Bombay.
    • For the implementation of rules, Decision tree is followed.
    • Presently, working on Nouns (Consonant-Vowel-Consonant Construction Completed).
 
Funded By: TDIL, Dept. Of Information Technology, Government Of India.
Copyright @2009 KashmiriZaban. All rights reserved.