Moses-support Digest, Vol 100, Issue 25

Send Moses-support mailing list submissions to
moses-support@mit.edu

To subscribe or unsubscribe via the World Wide Web, visit
http://mailman.mit.edu/mailman/listinfo/moses-support
or, via email, send a message with subject or body 'help' to
moses-support-request@mit.edu

You can reach the person managing the list at
moses-support-owner@mit.edu

When replying, please edit your Subject line so it is more specific
than "Re: Contents of Moses-support digest..."


Today's Topics:

1. Recasing and truecasing (Kenneth Heafield)
2. NLPPeople.com jobs: Machine Translation Software Developer in
the Netherlands (Maxim Khalilov)
3. running experiment.perl (mohamed hasanien)
4. Native 64-bit Windows support (Tom Hoar)


----------------------------------------------------------------------

Message: 1
Date: Fri, 06 Feb 2015 16:34:25 -0500
From: Kenneth Heafield <moses@kheafield.com>
Subject: [Moses-support] Recasing and truecasing
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <54D53361.6030609@kheafield.com>
Content-Type: text/plain; charset=utf-8

Dear Moses,

What are the experiences with truecasing v the recaser? It seems the
recaser's default does:

1) Train a truecaser
2) Truecase the monolingual data
3) Train an LM on the truecased data

There's an option to just directly go to LM training. Any thoughts on
which is better?

It just feels weird to use the truecaser, which applies a unigram
popularity model in some cases, to filter the training data for an
n-gram model (so it won't be able to make n-gram decisions about thsoe
words).

Kenneth


------------------------------

Message: 2
Date: Sat, 7 Feb 2015 02:42:23 +0400
From: Maxim Khalilov <maxkhalilov@gmail.com>
Subject: [Moses-support] NLPPeople.com jobs: Machine Translation
Software Developer in the Netherlands
To: mt-list@eamt.org, moses-support <moses-support@mit.edu>
Message-ID:
<CAPKeiSCR7+Lrh+HxizBcnxr2FSY2J6dvxfEKXgWfoLEU_fjinQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Infor is actively recruiting for a Software Developer to join our
Translation team, as a software engineer to support the Machine Translation
initiative team in Barneveld, The Netherlands. The Translation team
supports all Infor software products with translations.

Duties and responsibilities
? Develop programs and scripts to support and improve Machine Translation
? Automate the upload of content to the Machine Translation environment
? Train the engines of the Machine Translation solutions
? Interpret written business requirements to generate technical solutions
? Perform development to agreed technical standards
? Create and maintain technical documentation using defined technical
documentation templates
? Performs related duties as assigned

More and application form at
https://nlppeople.com/index.php/job/4707/machine-translation-software-developer-barneveld
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150207/4eb598ce/attachment-0001.htm

------------------------------

Message: 3
Date: Sat, 7 Feb 2015 02:01:29 +0000 (UTC)
From: mohamed hasanien <mhmd_hasnen@yahoo.com>
Subject: [Moses-support] running experiment.perl
To: Moses-support Support <moses-support@mit.edu>
Message-ID:
<447887057.1077238.1423274489091.JavaMail.yahoo@mail.yahoo.com>
Content-Type: text/plain; charset="utf-8"

Hi all?I get this error every time i try to run "experiment.perl"?STARTING UP AS PROCESS 13319 ON vps36962.vps.ovh.ca AT Fri Feb ?6 20:54:29 EST 2015LOAD CONFIG...working directory is ~/workingrunning experimental run number 0
ESTABLISH WHICH STEPS NEED TO BE RUN
FIND DEPENDENCIES BETWEEN STEPS
CHECKING IF OLD STEPS ARE RE-USABLE
DEFINE STEPS (run with -exec if everything ok)Cannot open: No such file or directory at /root/mosesdecoder/scripts/ems/experiment.perl line 3393.------------------how i can solve that error?
mohammed hassanien Mohammed
Egyption Programmers Vice-captain
01000121556
Egyption Programmers Syndicate
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150207/ddf0f54b/attachment-0001.htm

------------------------------

Message: 4
Date: Sat, 07 Feb 2015 23:33:22 +0700
From: Tom Hoar <tahoar@precisiontranslationtools.com>
Subject: [Moses-support] Native 64-bit Windows support
To: moses-support <moses-support@mit.edu>
Message-ID: <54D63E52.5060200@precisiontranslationtools.com>
Content-Type: text/plain; charset=utf-8; format=flowed

The most recent information I can find shows that following FF's were
available:

PhraseDictionaryMemory
PhraseDictionaryBinary
PhraseDictionaryOnDisk
LexicalReordering
KENLM

In R-3, processPhraseTable has been removed and PhraseDictionaryBinary
been earmarked for end-of-life. Does R-3 include native Windows support
for compact phrase and compact reordering formats? A quick review of the
source shows they might not support native Win64. I also seem to
remember some exchanges a few weeks ago about the compact
phrase/reordering code needs major updates.

If this is correct, what's the status on that and who's doing the work?
We'd like to help to make sure we add Win64 support.



------------------------------

_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support


End of Moses-support Digest, Vol 100, Issue 25
**********************************************

Tweet