Workshop on

"Shallow Parsing in South Asian Languages"

Softwares

  • Evaluation script is here It is an extension to the Conll-2000 evaluation script. Please use this to report results in your paper.
  • Sanchay is a collection of APIs and tools for NLP. Sanchay1.0 provides editor for Indian languages (hindi, telugu, bengali, punjabi etc..) without any font issues.

    • The README for installation/upgradation of this software is available here.
    • Download version 0.1 of the software as tgz or as zip file.
    • Exhaustive documentation of the software is available as tgz or as zip file.
    • Documentation for Sanchay Editor is here.

  • The training data has been released in Shakti Standard Format (SSF). A short note on SSF is here. For a detail ed description of the SSF format, please refer section 4 in this pdf .

  • A simple perl script to convert data in BIO format to SSF format is here . And the perl script to convert data in SSF format to BIO is here

 
[Top]