Moses-support Digest, Vol 120, Issue 11

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: Getting phrase-boundaries with moses' output (Hieu Hoang)
2. Re: Getting phrase-boundaries with moses' output (Nat Gillin)
3. Filtered vs Non-filtered Translation model (Nat Gillin)
4. Re: Filtered vs Non-filtered Translation model (Philipp Koehn)


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

Message: 1
Date: Mon, 10 Oct 2016 22:23:07 +0100
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Getting phrase-boundaries with moses'
output
To: Nat Gillin <nat.gillin@gmail.com>, moses-support@mit.edu
Message-ID: <89812f08-5cf0-d195-1950-55d90b54a167@gmail.com>
Content-Type: text/plain; charset="windows-1252"

I'm not sure what you mean. Try running

./moses ... -T [filename]

or

./moses ... -t


On 10/10/2016 10:54, Nat Gillin wrote:
> Dear Moses community,
>
> Is it possible for moses to generate some sort of phrase-boundaries
> together with the moses' decoded output? If so, how?
>
> Thank you in advance for the tips =)
>
> Regards,
> Liling
>
>
> _______________________________________________
> 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/20161010/7d89f20b/attachment-0001.html

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

Message: 2
Date: Tue, 11 Oct 2016 09:04:56 +0800
From: Nat Gillin <nat.gillin@gmail.com>
Subject: Re: [Moses-support] Getting phrase-boundaries with moses'
output
To: Hieu Hoang <hieuhoang@gmail.com>
Cc: moses-support@mit.edu
Message-ID:
<CAD2EOZikUGtv-Q2XvuWkB1O12ebj2aa9DSOai03UDV=ROWHr4w@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Thanks Hieu!!

Exactly what i needed =)

Regards,
Nat

On Tue, Oct 11, 2016 at 5:23 AM, Hieu Hoang <hieuhoang@gmail.com> wrote:

> I'm not sure what you mean. Try running
>
> ./moses ... -T [filename]
>
> or
>
> ./moses ... -t
>
> On 10/10/2016 10:54, Nat Gillin wrote:
>
> Dear Moses community,
>
> Is it possible for moses to generate some sort of phrase-boundaries
> together with the moses' decoded output? If so, how?
>
> Thank you in advance for the tips =)
>
> Regards,
> Liling
>
>
> _______________________________________________
> Moses-support mailing listMoses-support@mit.eduhttp://mailman.mit.edu/mailman/listinfo/moses-support
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20161010/23707ed9/attachment-0001.html

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

Message: 3
Date: Tue, 11 Oct 2016 11:41:56 +0800
From: Nat Gillin <nat.gillin@gmail.com>
Subject: [Moses-support] Filtered vs Non-filtered Translation model
To: moses-support@mit.edu
Message-ID:
<CAD2EOZjY34RfPvDfhW-OMdnyMMCa2sNAP72g-KTUW=BiRN3=jg@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Dear Moses community,

I have a question regarding filtered and non-filtered translation models,
is it a common methodology to always filter the models prior to testing?

Is it right that the filtering is to reduce the phrase-table and reordering
table size such that decoding is faster? Given the appropriate beam size
and more computing power the same accuracy (BLEU or otherwise) can also be
achieved without a filtering?

Regards,
Nat
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20161010/77cab3c6/attachment-0001.html

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

Message: 4
Date: Tue, 11 Oct 2016 09:42:41 -0400
From: Philipp Koehn <phi@jhu.edu>
Subject: Re: [Moses-support] Filtered vs Non-filtered Translation
model
To: Nat Gillin <nat.gillin@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAAFADDBuuaFbj4fT_9=O6n7qCQUG2gKC+sriL0jCEFvJsMrchQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Hi,

filtering was original introduced as a necessity to deal with memory usage
of the
translation model. Since then, the language models have become bigger and
the data structures to store the translation model more compact, so it may
not be
a useful step anymore.

There may be a bit of a speed effect, especially during startup, but it is
mainly
done for memory size.

-phi

On Mon, Oct 10, 2016 at 11:41 PM, Nat Gillin <nat.gillin@gmail.com> wrote:

> Dear Moses community,
>
> I have a question regarding filtered and non-filtered translation models,
> is it a common methodology to always filter the models prior to testing?
>
> Is it right that the filtering is to reduce the phrase-table and
> reordering table size such that decoding is faster? Given the appropriate
> beam size and more computing power the same accuracy (BLEU or otherwise)
> can also be achieved without a filtering?
>
> Regards,
> Nat
>
> _______________________________________________
> 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/20161011/2c4c8a94/attachment-0001.html

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

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


End of Moses-support Digest, Vol 120, Issue 11
**********************************************

Tweet