[Corpora-List] Summary -- Hindi parsers

From: Elliott Franco Drabek (edrabek@cs.jhu.edu)
Date: Sat Jun 14 2003 - 02:22:38 MET DST

  • Next message: Khalid CHOUKRI: "RE: [Corpora-List] Legal aspects of compiling corpora"

    Dear Colleagues,

    I am summarizing the results of my search for publicly available analyzers for
    Hindi.

    1. Emilie Guimier reminded me of the discussion in April of this year, in which
      Abhaya Agarwal gave a pointer to a morphological parser available from IIIT:

      http://www.iiit.net/ltrc/downloads.html

      and Mike Maxwell gave a pointer to another morphological parser by Vasu
      Renganathan:

      http://ccat.sas.upenn.edu/plc/tamilweb/hindi.html

    2. Ted Pedersen pointed out that corpora tagged with (unspecified) grammatical
      categories are available from

      http://tdil.mit.gov.in/download/menu.htm

      and that this might be used to train a tagger. I haven't been able to access
      the data, without a DOS system available, so I can't say what grammatical
      categories are marked.

    3. Web search lead me to Papi Reddy's homepage

      http://gdit.iiit.net/~papi_reddy/

      where he offers a phrase chunker for download.

    I hope this is helpful to someone.

    With thanks,

      - Elliott



    This archive was generated by hypermail 2b29 : Sat Jun 14 2003 - 02:27:53 MET DST