From kde-i18n-doc  Mon Mar 27 13:25:09 2000
From: Logi Ragnarsson <logir () logi ! org>
Date: Mon, 27 Mar 2000 13:25:09 +0000
To: kde-i18n-doc
Subject: Statistics based lexica
X-MARC-Message: https://marc.info/?l=kde-i18n-doc&m=95416349409317
MIME-Version: 1
Content-Type: multipart/mixed; boundary="--mojUlQ0s9EVzWg2t"


--mojUlQ0s9EVzWg2t
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: quoted-printable

Hi!

I've been experimentin a bit with statistidcs based guessing of translations
of single words and wrote a small utility to build a lexicon from a pile of
PO files. Some results (Icelandic, Italian and German but I can add more)
can be seen at http://www.logi.org/lexicon/guess/. I don't know how well it
works for other languages, but for Icelandic it is fair but not perfect. I
expect it will be better for German (more po files to work with) and Italian
(less disparity in the grammar) but I don't know. I don't know German and my
Italian is terrible.

If this looks useful I can automagically update these lists periaodically as
the PO's change and add more languages.

Bless,
Logi

--=20
Logi Ragnarsson (logir@logi.org)  |  Some day we all shall be out of scope
PGP/GPG key ID: 1024R/42935585    |  Sex, Maths & Rock'n'Roll!

--mojUlQ0s9EVzWg2t
Content-Type: application/pgp-signature

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.0.0 (GNU/Linux)
Comment: For info see http://www.gnupg.org

iQCVAwUBON9hMkqnHCFCk1WFAQEVqQP+IwCc9hCg9q4tEgL9a7mZSU8d3JWaAIbc
zjA6AP1XTfKemFr6/FWYCSyBztNu74Ecy+NolZMYWwdsfJ57mZCPuVY9tUM6AP4C
uTpAgF6vnG8TMq2F550UhqlZCK4KV0XIKvMYcn1tJc3h0KJKWwpZkr9hXXXDK4HI
8L12nR8RO9E=
=nKEa
-----END PGP SIGNATURE-----

--mojUlQ0s9EVzWg2t--