Re: [Corpora-List] Searching for Morphological Analyzers

From: Mike Maxwell (maxwell@ldc.upenn.edu)
Date: Thu Jun 24 2004 - 16:52:06 MET DST

  • Next message: Magali Jeanmaire: "[Corpora-List] ELRA News"

    (I replied to this earlier, but accidently only sent it to the original
    poster. Since unlike Linguist List, this list doesn't have a "reply to
    sender and let them summarize" policy--at least I don't think it
    does--I'm sending this to the list, in case there are others interested.
      Apologies if that's not kosher.)

    Navot Akiva wrote:

    > I'm a PhD student, and I'm searching for good (hopefully free)
    > morphological analyzers for English, Turkish, and Finnish and Hebrew .

    --------------------
    English:

    SIL provides the free 'Englex' grammar, which runs under their free
    PK-KIMMO parser http://www.sil.org/pckimmo/v2/englex.html,
    http://www.sil.org/pckimmo/about_pc-kimmo.html.

    --------------------
    Finnish: Commercial programs with demos:

    Fintwol developed by Kimmo Koskenniemi, and a company called Lingsoft. A
    demo is available at http://www.lingsoft.fi/cgi-bin/fintwol

    Xerox demo at
    http://www.xrce.xerox.com/competencies/content-analysis/demos/finnish.
    (Their web site frequently changes, so you may have to look around a bit
    to find this.)

    --------------------
    Turkish:

    A PC-KIMMO analyzer is available at
    http://www-2.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/nlp/morph/pc_kimmo/turklex/turklex.tgz

    Xerox and Bilkent University have done one more recently, but the links
    were dead the last time I checked. Some years ago, Jorge Hankamer, of
    UC Santa Cruz(?) had written a Turkish morphological parser in C. I
    don't know what the status of it is now.

    --------------------
    Hebrew:
    The web page at
    http://www.cs.technion.ac.il/~erelsgl/bxi/hmntx/teud_tokna.html#English
    includes source files for three parsers (including lexicon files) for a
    general perser (all parses), a probabilistic parser, and a parser that
    uses a syntactic parse (full? Partial?) to disambiguate. Should be
    buildable under Windows and Unix.

         Mike Maxwell
         Linguistic Data Consortium



    This archive was generated by hypermail 2b29 : Thu Jun 24 2004 - 16:59:21 MET DST