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: -lm training parameter (Read, James C)
2. Re: gappy phrases (Read, James C)
3. Re: [Question?]How to ensure that all N-best list will be
included in Moses search graph? (Hieu Hoang)
4. Re: gappy phrases (Kenneth Heafield)
5. The Apertium free/open-source machine translation project in
Google Code-In 2013 (Mikel L. Forcada)
----------------------------------------------------------------------
Message: 1
Date: Sun, 3 Nov 2013 21:57:04 +0000
From: "Read, James C" <jcread@essex.ac.uk>
Subject: Re: [Moses-support] -lm training parameter
To: Tom Hoar <tahoar@precisiontranslationtools.com>,
"moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<F00840E41983C645928E21E3C35F4EB1012CF34FFB@mbx1-node2.essex.ac.uk>
Content-Type: text/plain; charset="us-ascii"
Thanks.
So if you wanted to train and at a later date use a different LM with the already trained TM would it just be a simple case of manually editing moses.ini?
If I were to edit the training script to skip the check that LM file exists (it doesn't) it wouldn't break anything would it?
James
________________________________________
From: moses-support-bounces@mit.edu [moses-support-bounces@mit.edu] on behalf of Tom Hoar [tahoar@precisiontranslationtools.com]
Sent: 03 November 2013 13:03
To: moses-support@mit.edu
Subject: Re: [Moses-support] -lm training parameter
You are correct that train-model.perl script does not use the -lm
parameter through any of the word alignment or phrase scoring steps. The
script's step 9 builds a template moses.ini configuration file and
includes the values from the -lm parameter. At the beginning, the script
checks that the -lm value points to a non-zero length file. If the file
is missing or is zero length, the script halts.
On 11/03/2013 06:03 PM, Read, James C wrote:
> Hi,
>
> does anybody know what the effect of the -lm training parameter in the training script is? Surely the LM used has no effect on typical training tasks like word alignment and phrase scoring?
>
> thanks,
> James
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
------------------------------
Message: 2
Date: Sun, 3 Nov 2013 22:18:50 +0000
From: "Read, James C" <jcread@essex.ac.uk>
Subject: Re: [Moses-support] gappy phrases
To: Barry Haddow <bhaddow@staffmail.ed.ac.uk>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<F00840E41983C645928E21E3C35F4EB1012CF35009@mbx1-node2.essex.ac.uk>
Content-Type: text/plain; charset="us-ascii"
My understanding is that they used a similar approach as the grammar extraction to extract the gappy phrases. Would it be a massive undertaking to get Moses to support this?
James
________________________________________
From: Barry Haddow [bhaddow@staffmail.ed.ac.uk]
Sent: 30 October 2013 09:26
To: Read, James C
Cc: moses-support@mit.edu
Subject: Re: [Moses-support] gappy phrases
No, but it does support hiero and syntax models.
On 29/10/13 22:23, Read, James C wrote:
> Hi,
>
> does anybody know if Moses supports gappy phrases http://www-nlp.stanford.edu/pubs/naacl10-discontinuous_phrases.pdf
>
> James
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
------------------------------
Message: 3
Date: Mon, 4 Nov 2013 00:27:58 +0000
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] [Question?]How to ensure that all N-best
list will be included in Moses search graph?
To: LUONG Ngoc Quang <quangngocluong@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbhop1ybSfqX4HR1G3oQVk=2Hf2WMPDnfVW+gOT5dv4bvA@mail.gmail.com>
Content-Type: text/plain; charset="windows-1252"
can you please send me the output search graph and the n-best list for the
1 sentence where you are seeing this error.
Also, please send me the script you use to check whether a sentence is in
the graph.
I don't think it is possible for a sentence to be in the nbest list but not
in the search graph, but i will take a look
On 1 November 2013 14:17, LUONG Ngoc Quang <quangngocluong@gmail.com> wrote:
> Hi all,
> Currently i would like to exploit the Moses search graph as an alternative
> for N-best list to improve MT, thanks to a huge number of hypotheses it
> contains. Nevertheless when i try to output all the hypotheses in the
> search graph, i observe that they don't cover all N-best list. In other
> words, there are still several hypotheses in N-best (N=1000) not included
> in the search graph.
> Even when i increase the number of hypotheses popped for each stack (up to
> 10000 for example), this coverage can not be obtained.
> So, i would like to ask all of you whether we have any Moses option
> (command, script?) to ensure that the search graph will contain all N best
> list of each source sentence?
> For information, the command we invoked to generate the search graph and
> the N-best list is as follows:
>
> ./home/toolkits/Moses/moses-04-2009/moses-cmd/src/moses
> -f output10881/moses.ini
> -mbr -cube-pruning-pop-limit 10000
> -s 10000
> -output-search-graph search_graph_881
> -use-alignment-info
> -print-alignment-info
> -include-alignment-in-n-best
> -print-alignment-info-in-n-best -n-best-list ./Nbest-881test 1000
> < ./pre-processed-corpus/881.lowercased.fr
> > ./pre-processed-corpus/881.hyp.SG
>
> Furthermore, the way we conduct to extract all hypotheses (sentences) from
> the search graph is : We start from each final node, move backward until
> reach the initial one. First, the hypothesis is set : s= "". In each step,
> we get the field "out" of the current node (the translated word(s)) and add
> to the hypothesis : s = out + s.
> Is this the right way to obtain all hypotheses?
>
> Thanks a lot and all suggestions would be very welcomed !
> bests,
> Quang
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
--
Hieu Hoang
Research Associate
University of Edinburgh
http://www.hoang.co.uk/hieu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20131104/c3ab2a01/attachment-0001.htm
------------------------------
Message: 4
Date: Sun, 03 Nov 2013 20:34:02 -0800
From: Kenneth Heafield <moses@kheafield.com>
Subject: Re: [Moses-support] gappy phrases
To: moses-support@mit.edu
Message-ID: <527723BA.9050304@kheafield.com>
Content-Type: text/plain; charset=ISO-8859-1
Hi,
I'll throw in the anecdote that gappy phrases are currently not in use
at Stanford. My predecessor told me that it took a lot longer and only
improved BLEU slightly on Chinese-English. But it's also possible that
something didn't get passed down correctly from Michel to my predecessor
to me. . .
Kenneth
On 11/03/13 14:18, Read, James C wrote:
> My understanding is that they used a similar approach as the grammar extraction to extract the gappy phrases. Would it be a massive undertaking to get Moses to support this?
>
> James
> ________________________________________
> From: Barry Haddow [bhaddow@staffmail.ed.ac.uk]
> Sent: 30 October 2013 09:26
> To: Read, James C
> Cc: moses-support@mit.edu
> Subject: Re: [Moses-support] gappy phrases
>
> No, but it does support hiero and syntax models.
>
> On 29/10/13 22:23, Read, James C wrote:
>> Hi,
>>
>> does anybody know if Moses supports gappy phrases http://www-nlp.stanford.edu/pubs/naacl10-discontinuous_phrases.pdf
>>
>> James
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>
>
> --
> The University of Edinburgh is a charitable body, registered in
> Scotland, with registration number SC005336.
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
------------------------------
Message: 5
Date: Mon, 04 Nov 2013 08:36:13 +0100
From: "Mikel L. Forcada" <mlf@dlsi.ua.es>
Subject: [Moses-support] The Apertium free/open-source machine
translation project in Google Code-In 2013
To: moses-support@mit.edu
Message-ID: <52774E6D.8050103@dlsi.ua.es>
Content-Type: text/plain; charset="iso-8859-1"
*The Apertium free/open-source machine translation project in Google
Code-In 2013*
[Apologies for multiple postings]
The *Apertium project* [1], which develops a free/open-source rule-based
machine translation platform, is, for the fourth year in a row, one of
the 10 free/open-source organizations [3] participating in the Google
Code-In.
*Google Code-In* [3] is a contest to introduce pre-university students
(aged 13 to 17) to free/open-source software development. Students from
all around the world can participate by tackling small tasks, which may
include code writing, debugging, documentation, production of training
material, etc. For each three tasks, students get a Google Code-In
T-shirt. Each organization, in this case Apertium, will select two
winners of the Grand Prize: a trip to the Google headquarters for the
students and a parent or tutor.
Project Apertium has proposed *a wide variety of tasks* [4], including
the creation of documentation to help users and developers, the
development of dictionaries and rules for new or existing languages, the
development of programs to transform other existing free/open-source
resources to Apertium format or to use Apertium machine translation from
other existing software, etc. There are also debugging and quality
assessment tasks, or even tasks where texts are annotated so that they
can be used to test and train Apertium modules.
*Students* have already come around to the Apertium IRC channel [5] to
ask about tasks, even if the contest does not officially start until
November 16, and *mentors* (around 20 in Apertium this year [4]) have
already started to guide them.
If you are a pre-university student or know one that would be interested
in involving in free/open-source development of machine translation,
tell them to come around and get involved.
[1] http://www.apertium.org
[2] http://www.google-melange.com/gci/accepted_orgs/google/gci2013
[3] https://code.google.com/p/google-code-in/
[4] Current list:
http://wiki.apertium.org/wiki/Task_ideas_for_Google_Code-in
[5] #apertium at irc.freenode.ne
--
Mikel L. Forcada (http://www.dlsi.ua.es/~mlf/)
Departament de Llenguatges i Sistemes Inform?tics
Universitat d'Alacant
E-03071 Alacant, Spain
Phone: +34 96 590 9776
Fax: +34 96 590 9326
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20131104/715058bc/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 85, Issue 4
********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 85, Issue 4"
Post a Comment