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. One sided factor based model (Tin Pavelic)
2. Re: One sided factor based model (Philipp Koehn)
3. Re: Sentence mismatch error! (Matthias Huck)
4. Re: Sentence mismatch error! (Philipp Koehn)
----------------------------------------------------------------------
Message: 1
Date: Thu, 09 Oct 2014 13:35:52 +0200
From: Tin Pavelic <tin.pavelic@gmail.com>
Subject: [Moses-support] One sided factor based model
To: moses-support@mit.edu
Message-ID: <54367318.5090604@gmail.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Hi support,
I just wanted to ask is there any use of creating model with POS and
lemma only on one language. Since i am translating from english to cycL
i only have those information for the source languge.
Is that enough??
Thanks in advance,
--
__________________________
Tin Pavelic
__________________________
------------------------------
Message: 2
Date: Thu, 9 Oct 2014 09:29:02 -0400
From: Philipp Koehn <pkoehn@inf.ed.ac.uk>
Subject: Re: [Moses-support] One sided factor based model
To: Tin Pavelic <tin.pavelic@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAAFADDCLZm+egOwXoHTk0si6PFq4nYYcw_9S6xw1g8Z=d2KqFg@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
Hi,
I can think of some reasons why POS and lemma information in the
source language may:
- help you to disambiguate words that have the same surface form but
different POS
(for instance in German "das" as determiner or relative pronoun)
- allow you to back-off to the translation from the lemma, if the
morphologically
inflected form is unknown.
- add a lexicalized reordering models based on POS for syntax-driven reordering
-phi
On Thu, Oct 9, 2014 at 7:35 AM, Tin Pavelic <tin.pavelic@gmail.com> wrote:
> Hi support,
>
> I just wanted to ask is there any use of creating model with POS and
> lemma only on one language. Since i am translating from english to cycL
> i only have those information for the source languge.
>
> Is that enough??
>
> Thanks in advance,
> --
> __________________________
>
> Tin Pavelic
> __________________________
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
------------------------------
Message: 3
Date: Thu, 09 Oct 2014 15:49:30 +0100
From: Matthias Huck <mhuck@inf.ed.ac.uk>
Subject: Re: [Moses-support] Sentence mismatch error!
To: Arefeh Kazemi <arefeh_kazemi@yahoo.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <1412866170.2170.53.camel@portedgar>
Content-Type: text/plain; charset="UTF-8"
Hi Arefeh,
Have you been able to resolve that issue? Maybe one of your GIZA
alignments is flawed, for instance because the GIZA process was
terminated before is finished. Did you check that both the standard and
the inverse alignment files have the same number of lines?
Check it like this:
$ zcat training/giza.1/de-en.A3.final.gz | wc -l; zcat training/giza-inverse.1/en-de.A3.final.gz | wc -l
900000
501713
In that case there would be a problem and you'd have to rerun GIZA in
the inverse direction. If you get the same number of lines and it
matches what you expect to get from your corpus, then it's a different
issue and you have to investigate further.
Cheers,
Matthias
On Mon, 2014-10-06 at 03:13 -0700, Arefeh Kazemi wrote:
> Hi
> I have re-installed moses on my system but I have a problem with giza
> - symmetrize step.
> it gets some errors of this type:
> Sentence mismatch error! Line #501714
> Sentence mismatch error! Line #501715
> .
> .
> .
> Sentence mismatch error! Line #900000
>
>
> all of my data files are in utf8 format and I have run moses
> successfully on these files before.
>
>
> any suggestion to fix the problem would be appreciated.
>
>
> Regards
> Arefeh
>
>
>
>
> _______________________________________________
> 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: 4
Date: Thu, 9 Oct 2014 11:08:31 -0400
From: Philipp Koehn <pkoehn@inf.ed.ac.uk>
Subject: Re: [Moses-support] Sentence mismatch error!
To: Matthias Huck <mhuck@inf.ed.ac.uk>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>, Arefeh Kazemi
<arefeh_kazemi@yahoo.com>
Message-ID:
<CAAFADDCQU0SCGMDxo=WksnXV6QL-jLM6S8+7TRgDDCOOfR-dEA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi,
this may be also caused by having too long / empty / length-mismatched
sentences
when running GIZA. Make sure to run the clean-corpus-n.perl script first.
-phi
On Thu, Oct 9, 2014 at 10:49 AM, Matthias Huck <mhuck@inf.ed.ac.uk> wrote:
> Hi Arefeh,
>
> Have you been able to resolve that issue? Maybe one of your GIZA
> alignments is flawed, for instance because the GIZA process was
> terminated before is finished. Did you check that both the standard and
> the inverse alignment files have the same number of lines?
>
> Check it like this:
>
> $ zcat training/giza.1/de-en.A3.final.gz | wc -l; zcat
> training/giza-inverse.1/en-de.A3.final.gz | wc -l
> 900000
> 501713
>
> In that case there would be a problem and you'd have to rerun GIZA in
> the inverse direction. If you get the same number of lines and it
> matches what you expect to get from your corpus, then it's a different
> issue and you have to investigate further.
>
> Cheers,
> Matthias
>
>
> On Mon, 2014-10-06 at 03:13 -0700, Arefeh Kazemi wrote:
> > Hi
> > I have re-installed moses on my system but I have a problem with giza
> > - symmetrize step.
> > it gets some errors of this type:
> > Sentence mismatch error! Line #501714
> > Sentence mismatch error! Line #501715
> > .
> > .
> > .
> > Sentence mismatch error! Line #900000
> >
> >
> > all of my data files are in utf8 format and I have run moses
> > successfully on these files before.
> >
> >
> > any suggestion to fix the problem would be appreciated.
> >
> >
> > Regards
> > Arefeh
> >
> >
> >
> >
> > _______________________________________________
> > 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
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20141009/0b16f3bb/attachment-0001.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 96, Issue 13
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 96, Issue 13"
Post a Comment