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. Re: Problem on Giza-pp (Hieu Hoang)
2. Re: Tuning returns all zero weights for hierarchical
phrase-based model (Hieu Hoang)
----------------------------------------------------------------------
Message: 1
Date: Mon, 13 Apr 2015 00:12:41 +0400
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Problem on Giza-pp
To: moses-support@mit.edu, siyuan-jing@hotmail.com
Message-ID: <552AD1B9.2000804@gmail.com>
Content-Type: text/plain; charset="utf-8"
I just compiled ok it on redhat 6.2, gcc 4.9.1.
I got the code from here:
https://github.com/moses-smt/giza-pp
I'm not sure where you got v. 1.0.3.
You shouls get giza++ directly from github. Also, mgiza might be a
better alternative as it's maintained by more people and works with
multi-core machines
On 10/04/2015 04:52, siyuan-jing@hotmail.com wrote:
> Dear Moses Support Team,
> Today, I met a problem when I compiled Giza++.
> The version of Giza++ is v1.0.3.
> OS is CentOS 6.4, the version of gcc is 4.4.7
> The compiling information is shown below:
> Thank you for your help!
> Best regards.
> ------------------------------------------------------------------------
> siyuan-jing@hotmail.com
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150413/117c544c/attachment-0001.htm
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/png
Size: 12828 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20150413/117c544c/attachment-0001.png
------------------------------
Message: 2
Date: Mon, 13 Apr 2015 08:18:58 +0400
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Tuning returns all zero weights for
hierarchical phrase-based model
To: Shiman Guo <shim@brandeis.edu>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbjQdixpztXaQ-kTZsXAkMREN5=zgGfsvM_MnEau_bWqXQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
strange, how many iteration does it do? I use mert with hierarchical model
all the time, it works ok. This is the exact command for 1 of my runs:
/home/s0565741/workspace/github/mosesdecoder.hieu/scripts/training/
mert-moses.pl
/home/s0565741/workspace/experiment/nc/de-en/tuning/input.lc.1
/home/s0565741/workspace/experiment/nc/de-en/tuning/reference.lc.1
/home/s0565741/workspace/github/mosesdecoder.hieu/bin/moses
/home/s0565741/workspace/experiment/nc/de-en/tuning/moses.filtered.ini.2
--nbest 100 --working-dir
/home/s0565741/workspace/experiment/nc/de-en/tuning/tmp.2 --decoder-flags
"-threads 32 -v 0 " --rootdir
/home/s0565741/workspace/github/mosesdecoder.hieu/scripts -mertdir
/home/s0565741/workspace/github/mosesdecoder.hieu/bin -threads 32
--no-filter-phrase-table
Hieu Hoang
Researcher
New York University, Abu Dhabi
http://www.hoang.co.uk/hieu
On 9 April 2015 at 17:08, Shiman Guo <shim@brandeis.edu> wrote:
> Hi all,
>
> I was trying to train and tune a baseline hierarchical phrase-based model,
> following the baseline tutorial (with additional options to `
> train-model.pl`). While the training was efficient and successful, the
> tuning process always gave me an all zero weights in the `moses.ini`.
>
> The command I used for tuning was:
>
> ${MOSES-ROOT}/scripts/training/mert-moses.pl \
> ${CHN-DEVSET} ${ENG-DEVSET} \
> ${MOSES-ROOT}/bin/moses ./model/moses.ini \
> --mertdir ${MOSES-ROOT}/bin/
>
> It worked fine with a phrase-based model. So I think the installation
> should be good. And I also tried to use mose_chart as the decoder, but
> there was no gain.
>
> Has anyone else run into this issue? Please advise.
>
>
> Best,
> Shiman
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150413/430b8243/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 102, Issue 22
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 102, Issue 22"
Post a Comment