Home » Uncategories » Moses-support Digest, Vol 85, Issue 8

Moses-support Digest, Vol 85, Issue 8

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: gappy phrases (Daniel Cer)
2. Re: gappy phrases (Read, James C)
3. Re: gappy phrases (Hieu Hoang)


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

Message: 1
Date: Mon, 4 Nov 2013 11:43:03 -0800
From: Daniel Cer <daniel.cer@gmail.com>
Subject: Re: [Moses-support] gappy phrases
To: Kenneth Heafield <moses@kheafield.com>
Cc: moses-support@mit.edu
Message-ID:
<CAMwt5UJDS16EGiDxr=Le=WotKOK1zY-CKK+KP4i4_CbBPckLVw@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

Hi everyone,

Ken and I just spoke about this.

Here's a quick synopsis of our semi-recent experience at Stanford with
discontinuous/gappy phrases:

- Source side gaps are effectively free and don't really degrade
decoding time.
- Target side gaps are fine for smaller beam sizes (e.g., < 200).
- When using large beams, our current implementation slows down
dramatically. For example, with a stack size of 500, I think it was
sometimes taking over an hour to translate some sentences.

While discontinuous phrases can moderately increase the BLEU score, but we
get a bigger increase by just using very large beam sizes.

Dan



On Sun, Nov 3, 2013 at 8:34 PM, Kenneth Heafield <moses@kheafield.com>wrote:

> 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
> >
> _______________________________________________
> 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/20131104/5db2a9a1/attachment-0001.htm

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

Message: 2
Date: Tue, 5 Nov 2013 07:29:27 +0000
From: "Read, James C" <jcread@essex.ac.uk>
Subject: Re: [Moses-support] gappy phrases
To: Daniel Cer <daniel.cer@gmail.com>, Kenneth Heafield
<moses@kheafield.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<F00840E41983C645928E21E3C35F4EB1012CF351C5@mbx1-node2.essex.ac.uk>
Content-Type: text/plain; charset="iso-8859-1"

Interesting.

This isn't going to be an issue for the kind of experiments I will be running, though. I won't be using a language model or a reordering model or a beam search during decoding (I know, not much of Moses left). My main usage of 'Moses' at the moment is training translation models so I can run experiments with 'units of translation' in isolation from other variables in the system (language model, reordering model, beam search). I would really like to be able to run some experiments also with discontinuous phrases both source side and target side.

Any idea what kind of changes I would need to make to the training process to be able to learn these kind of transformations? I suppose I'm also going to need to modify the operation of the translation model to get these working as well.

thanks,
James

________________________________
From: moses-support-bounces@mit.edu [moses-support-bounces@mit.edu] on behalf of Daniel Cer [daniel.cer@gmail.com]
Sent: 04 November 2013 19:43
To: Kenneth Heafield
Cc: moses-support@mit.edu
Subject: Re: [Moses-support] gappy phrases

Hi everyone,

Ken and I just spoke about this.

Here's a quick synopsis of our semi-recent experience at Stanford with discontinuous/gappy phrases:

* Source side gaps are effectively free and don't really degrade decoding time.
* Target side gaps are fine for smaller beam sizes (e.g., < 200).
* When using large beams, our current implementation slows down dramatically. For example, with a stack size of 500, I think it was sometimes taking over an hour to translate some sentences.

While discontinuous phrases can moderately increase the BLEU score, but we get a bigger increase by just using very large beam sizes.

Dan



On Sun, Nov 3, 2013 at 8:34 PM, Kenneth Heafield <moses@kheafield.com<mailto:moses@kheafield.com>> wrote:
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<mailto:bhaddow@staffmail.ed.ac.uk>]
> Sent: 30 October 2013 09:26
> To: Read, James C
> Cc: moses-support@mit.edu<mailto: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<mailto: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<mailto:Moses-support@mit.edu>
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu<mailto:Moses-support@mit.edu>
http://mailman.mit.edu/mailman/listinfo/moses-support




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

Message: 3
Date: Tue, 5 Nov 2013 12:12:52 +0000
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] gappy phrases
To: "Read, James C" <jcread@essex.ac.uk>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>, Daniel Cer
<daniel.cer@gmail.com>
Message-ID:
<CAEKMkbjnGkyMTSS6Dn9zd4HnnztGDcuyinV-ZG7d7Er6MaDnOA@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

If you're gonna throw most of Moses away, you may consider using and
extending the basic decoder I've just added to github

https://github.com/moses-smt/mosesdecoder/tree/master/contrib/basic-decoder

Or write your own. You're welcome to add it to moses too


On 5 November 2013 07:29, Read, James C <jcread@essex.ac.uk> wrote:

> Interesting.
>
> This isn't going to be an issue for the kind of experiments I will be
> running, though. I won't be using a language model or a reordering model or
> a beam search during decoding (I know, not much of Moses left). My main
> usage of 'Moses' at the moment is training translation models so I can run
> experiments with 'units of translation' in isolation from other variables
> in the system (language model, reordering model, beam search). I would
> really like to be able to run some experiments also with discontinuous
> phrases both source side and target side.
>
> Any idea what kind of changes I would need to make to the training process
> to be able to learn these kind of transformations? I suppose I'm also going
> to need to modify the operation of the translation model to get these
> working as well.
>
> thanks,
> James
>
> ________________________________
> From: moses-support-bounces@mit.edu [moses-support-bounces@mit.edu] on
> behalf of Daniel Cer [daniel.cer@gmail.com]
> Sent: 04 November 2013 19:43
> To: Kenneth Heafield
> Cc: moses-support@mit.edu
> Subject: Re: [Moses-support] gappy phrases
>
> Hi everyone,
>
> Ken and I just spoke about this.
>
> Here's a quick synopsis of our semi-recent experience at Stanford with
> discontinuous/gappy phrases:
>
> * Source side gaps are effectively free and don't really degrade
> decoding time.
> * Target side gaps are fine for smaller beam sizes (e.g., < 200).
> * When using large beams, our current implementation slows down
> dramatically. For example, with a stack size of 500, I think it was
> sometimes taking over an hour to translate some sentences.
>
> While discontinuous phrases can moderately increase the BLEU score, but we
> get a bigger increase by just using very large beam sizes.
>
> Dan
>
>
>
> On Sun, Nov 3, 2013 at 8:34 PM, Kenneth Heafield <moses@kheafield.com
> <mailto:moses@kheafield.com>> wrote:
> 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<mailto:
> bhaddow@staffmail.ed.ac.uk>]
> > Sent: 30 October 2013 09:26
> > To: Read, James C
> > Cc: moses-support@mit.edu<mailto: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<mailto: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<mailto:Moses-support@mit.edu>
> > http://mailman.mit.edu/mailman/listinfo/moses-support
> >
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu<mailto: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
>



--
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/20131105/7e55dcb3/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 8
********************************************

0 Response to "Moses-support Digest, Vol 85, Issue 8"

Post a Comment

Subscribe to: Post Comments (Atom)