Corpora: alignment programs

From: Tomaz Erjavec (Tomaz.Erjavec@ijs.si)
Date: Tue May 16 2000 - 13:29:50 MET DST

  • Next message: David Yarowsky: "Corpora: SIGDAT 2000 CFP - Empirical Methods in NLP and Very Large Corpora"

    Hi,
    there is a vanilla implementation in C at

    see http://nl.ijs.si/ME/CD/tool/Vanilla/

    From the README:

    Vanilla Aligner, V1.0

    AUTHORS:
      Pernilla Danielsson and Daniel Ridings
      Språkbanken
      Institutionen för svenska språket
      Göteborgs universitet
      S-412 98 Göteborg SWEDEN

    DOCUMENTATION:
      http://svenska.gu.se/PEDANT/workshop/workshop.html

    the above URL has alas gone but a copy is available from
    http://nl.ijs.si/telri/cat/Vanilla/ljubljana/

    Hope this helps,
    Tomaz

    Marco Antonio Esteves da Rocha writes:
    >
    > Dear all:
    >
    > I would like to carry out a few tests with an alignment program. I have
    > read the Gale and Church (1993) paper and, as you know, it comes with the
    > code. Before actually transcribing it:
    >
    > 1. Can I get it machine-readable anywhere ?
    > 2. Will it compile and run in my PC on a Mandrake Linux ?
    > 3. Has anyone run tests ?
    > 4. Any other more recent or easier options ?
    > 5. Are there any options that run in Windows (many students resist working
    > with anything but Windows) ?
    >
    > At the moment, the actual purpose of the request is teaching, as part
    > of a corpus linguistics course. So it is just a demo, but I would like it
    > to be as real-life-like as possible, and it may develop into an actual
    > full-fledged research initiative. Languages involved are English and
    > Portuguese, so far, Spanish should be included soon.
    >
    > Thanks
    >
    > Marco Rocha
    > marcor@cce.ufsc.br
    >
    >



    This archive was generated by hypermail 2b29 : Tue May 16 2000 - 13:28:41 MET DST