Re: [Corpora-List] starting a machine translation project

From: Francis Bond (fcbond@gmail.com)
Date: Thu Sep 14 2006 - 02:58:54 MET DST

  • Next message: TadPiotr: "[Corpora-List] corpus analysis of loanwords"

    G'day,

    There was some work on Indonesian MT in the CICC project
    <http://www.cicc.or.jp/english/kyoudou/mt.html>, which ended up with a
    fairly useful lexicon Indonesian-English on CD-ROM. If you email CICC
    then you should be a be able to get a copy. There are two relevant
    CDs, the Indonesian one, and the terminological one, which includes a
    technical lexicon for English, Malay, Thai, Indonesian, Chinese and
    Japanese.

    A lexicon is essential for rule- based MT and also a useful tool for
    aligning and backing-off in statistical MT. 

    -- 
Francis Bond  <www.kecl.ntt.co.jp/icl/mtg/members/bond/>
NTT Communication Science Laboratories | Natural Language Research Group

    P.S. Here is a sample entry:

    @2110IVMT
&2111mengabadikan
&2112135
&2113630
#2100to preserve; to keep alive; to immortalize
#2101IVABS
#2110to perpetuate
#2111IVABS
#2120to memorialize
#2121IVABS
#2130to capture (on canvas, etc.)
#2131IVABS
#2140to take a picture of; to photograph
#2141IVABS

    This archive was generated by hypermail 2b29 : Thu Sep 14 2006 - 21:18:38 MET DST