home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
ftp.cs.arizona.edu
/
ftp.cs.arizona.edu.tar
/
ftp.cs.arizona.edu
/
icon
/
newsgrp
/
group93a.txt
/
000109_icon-group-sender _Thu Apr 1 10:31:01 1993.msg
< prev
next >
Wrap
Internet Message Format
|
1993-04-21
|
1KB
Received: by cheltenham.cs.arizona.edu; Sat, 10 Apr 1993 05:35:21 MST
Date: 1 Apr 93 10:31:01 GMT
From: mercury.hsi.com!mlfarm!cs.arizona.edu!icon-group@uunet.uu.net
Subject: Language Translators and Artificial Languages
Message-Id: <9304011031.AA19688@medinah.atc.ucarb.com>
Sender: icon-group-request@cs.arizona.edu
To: icon-group@cs.arizona.edu
Status: R
Errors-To: icon-group-errors@cs.arizona.edu
>Date: Wed, 31 Mar 93 23:27:16 +0200
>From: job@rna.indiv.nluug.nl (Job van Zuijlen)
use of examples, statistics and analogy. The idea is that an MT system does
>not have to explain how a human translator translates, it only has to
>translate, i.e. has to give the same results a human translator would give.
>Examples of those results can be found in bilingual or multilingual text
>corpora; texts with translations in one or more languages. There are various
>ways to go from here: an overview of various approaches can be found in
>"An Introduction to Machine Translation" by Hutchins & Somers, Academic Press
>1992.
>
>Job van Zuijlen,
>Utrecht, Netherlands
>job@rna.indiv.nluug.nl
Yes. I'd heard several years ago of a project or product based on the
Canadian Parliamentary records. My impression was that it was the most
successful MT work of its time. As Jv Zuijlen above points out, having a
good corpus is an advantage.
Forrest Richey