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: n-best-list diversity (Matthias Huck)
2. Re: n-best-list diversity (Marcin Junczys-Dowmunt)
3. Re: n-best-list diversity (Matthias Huck)
4. Tools for Post-Editing that Preserve Alignments? (Graham Neubig)
5. Re: Supporting lattice input in Moses server (Hieu Hoang)
6. Re: Supporting lattice input in Moses server (Hala Almaghout)
----------------------------------------------------------------------
Message: 1
Date: Thu, 05 Jun 2014 18:17:23 +0100
From: Matthias Huck <mhuck@inf.ed.ac.uk>
Subject: Re: [Moses-support] n-best-list diversity
To: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <1401988643.2309.1860.camel@portedgar>
Content-Type: text/plain; charset="UTF-8"
Hi Marcin,
You can increase the n-best factor:
-n-best-factor 100
Or just set it to 0 (= no limit). The default is 20.
Cheers,
Matthias
On Thu, 2014-06-05 at 17:23 +0200, Marcin Junczys-Dowmunt wrote:
> Hi list,
> is there a way to make the n-best list in Moses a little bit more
> diverse without increasing the maximum n-best list size? Let's say I am
> willing to sacrifice decoding speed.
>
> For instance
>
> -n-best-list file 100 distinct
>
> generates 100 and collapses them, so sometimes there may be only one
> hypothesis. I can get more distinct hypotheses by setting the size to
> e.g. 1000, but then some sentences might actually come up with 1000
> distinct hypotheses which is overkill.
>
> The options -cube-pruning-diversity and -stack-diversity sound
> promising. I should add that this is a minolingual task with reordering
> switched off. I understand this has some impact on these options?
> Best,
> Marcin
> _______________________________________________
> 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: 2
Date: Thu, 05 Jun 2014 20:15:34 +0200
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: Re: [Moses-support] n-best-list diversity
To: Matthias Huck <mhuck@inf.ed.ac.uk>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <5390B3C6.8040206@amu.edu.pl>
Content-Type: text/plain; charset=UTF-8; format=flowed
Hi Matthias,
this doesn't do much for me. What exactly is this parameter intended
for? I admit the option description is not telling me anything.
Setting "-sd 10" for stack decoding with "-n-best-list file 100
distinct" seems to help. I am getting distinct n-best lists with at most
100 items and they seem to be a little bit better filled than with -sd 0.
With cube pruning, "-cbd some_number" does not seem to do anything, I
also tried to increase the pop limit with no success.
Best,
Marcin
W dniu 05.06.2014 19:17, Matthias Huck pisze:
> Hi Marcin,
>
> You can increase the n-best factor:
>
> -n-best-factor 100
>
> Or just set it to 0 (= no limit). The default is 20.
>
> Cheers,
> Matthias
>
>
> On Thu, 2014-06-05 at 17:23 +0200, Marcin Junczys-Dowmunt wrote:
>> Hi list,
>> is there a way to make the n-best list in Moses a little bit more
>> diverse without increasing the maximum n-best list size? Let's say I am
>> willing to sacrifice decoding speed.
>>
>> For instance
>>
>> -n-best-list file 100 distinct
>>
>> generates 100 and collapses them, so sometimes there may be only one
>> hypothesis. I can get more distinct hypotheses by setting the size to
>> e.g. 1000, but then some sentences might actually come up with 1000
>> distinct hypotheses which is overkill.
>>
>> The options -cube-pruning-diversity and -stack-diversity sound
>> promising. I should add that this is a minolingual task with reordering
>> switched off. I understand this has some impact on these options?
>> Best,
>> Marcin
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>
>
------------------------------
Message: 3
Date: Thu, 05 Jun 2014 19:29:54 +0100
From: Matthias Huck <mhuck@inf.ed.ac.uk>
Subject: Re: [Moses-support] n-best-list diversity
To: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Cc: moses-support <moses-support@mit.edu>
Message-ID: <1401992994.2309.1869.camel@portedgar>
Content-Type: text/plain; charset="UTF-8"
Hi Marcin,
It stops the loop for producing n-best translations from the search
graph after a maximum of (nBestFactor * desiredNBestSize) iterations.
Depending on the value of nBestFactor and the amount of identical
candidates that are seen, you might end up with only a few distinct
entries in your n-best list even for longer input sentences.
Cf. Manager::CalcNBest() in moses/Manager.cpp
This is purely about the n-best list output and does not affect search
in any way. If your problem is caused by pruning, then you need to look
into other parameters.
Cheers,
Matthias
On Thu, 2014-06-05 at 20:15 +0200, Marcin Junczys-Dowmunt wrote:
> Hi Matthias,
> this doesn't do much for me. What exactly is this parameter intended
> for? I admit the option description is not telling me anything.
>
> Setting "-sd 10" for stack decoding with "-n-best-list file 100
> distinct" seems to help. I am getting distinct n-best lists with at most
> 100 items and they seem to be a little bit better filled than with -sd 0.
>
> With cube pruning, "-cbd some_number" does not seem to do anything, I
> also tried to increase the pop limit with no success.
> Best,
> Marcin
>
> W dniu 05.06.2014 19:17, Matthias Huck pisze:
> > Hi Marcin,
> >
> > You can increase the n-best factor:
> >
> > -n-best-factor 100
> >
> > Or just set it to 0 (= no limit). The default is 20.
> >
> > Cheers,
> > Matthias
> >
> >
> > On Thu, 2014-06-05 at 17:23 +0200, Marcin Junczys-Dowmunt wrote:
> >> Hi list,
> >> is there a way to make the n-best list in Moses a little bit more
> >> diverse without increasing the maximum n-best list size? Let's say I am
> >> willing to sacrifice decoding speed.
> >>
> >> For instance
> >>
> >> -n-best-list file 100 distinct
> >>
> >> generates 100 and collapses them, so sometimes there may be only one
> >> hypothesis. I can get more distinct hypotheses by setting the size to
> >> e.g. 1000, but then some sentences might actually come up with 1000
> >> distinct hypotheses which is overkill.
> >>
> >> The options -cube-pruning-diversity and -stack-diversity sound
> >> promising. I should add that this is a minolingual task with reordering
> >> switched off. I understand this has some impact on these options?
> >> Best,
> >> Marcin
> >> _______________________________________________
> >> 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: Fri, 6 Jun 2014 11:54:53 +0900
From: Graham Neubig <neubig@is.naist.jp>
Subject: [Moses-support] Tools for Post-Editing that Preserve
Alignments?
To: "<moses-support@mit.edu>" <moses-support@mit.edu>
Message-ID:
<CADkjOCMgJ9pCa9eQGtU_Mgfn5BjW0asXutcJthZvh13tYGVvDw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Dear Moses Mailing List,
I apologize in advance for the somewhat off-topic post, but I was hoping
that someone might have an answer:
We're looking to do some post-editing experiments where we need both the
post-editing output and accurate alignments between the original system
output and the post-edited text indicating which words/phrases were
corrected into what. I have heard rumors that the NIST HTER tool was able
to do this, but I don't have access to the tool, and I wasn't able to find
any other available software that had this capability. Is anyone aware of a
good UI that makes it possible to do this?
Thanks in advance!
Graham
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140606/66886038/attachment-0001.htm
------------------------------
Message: 5
Date: Fri, 6 Jun 2014 09:54:21 +0100
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Supporting lattice input in Moses server
To: Hala Almaghout <halmaghout@computing.dcu.ie>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbgmn1-YXNTjfAu-F-_VXZW6CtrZcBtF3SeXOX1cZJaRQw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
there's no reason it shouldn't. Have you tried it?
On 3 June 2014 14:43, Hala Almaghout <halmaghout@computing.dcu.ie> wrote:
> Hi,
>
> Does Moses server support lattice input?
>
>
> Best,
>
> Hala
>
> _______________________________________________
> 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/20140606/c57b17e1/attachment-0001.htm
------------------------------
Message: 6
Date: Fri, 6 Jun 2014 10:44:31 +0100
From: Hala Almaghout <halmaghout@computing.dcu.ie>
Subject: Re: [Moses-support] Supporting lattice input in Moses server
To: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAE9fu9Xpn3ujmn08TncuD1JOo=zhno_nuAU9VVFiTNsC5XR3GA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Hi Hieu,
Yes I tried mosses server with lattice input using this command to start
the server:
mosesserver --server-port 9090 -inputtype 2 -f moses.ini -threads 8
However it seems that the lattice is never recognised, it's translated
literally with brackets and commas.
I used the same moses.ini file with normal moses and the lattice was
recognised and translated correctly.
Many thanks,
Best,
Hala
On 6 June 2014 09:54, Hieu Hoang <Hieu.Hoang@ed.ac.uk> wrote:
> there's no reason it shouldn't. Have you tried it?
>
>
> On 3 June 2014 14:43, Hala Almaghout <halmaghout@computing.dcu.ie> wrote:
>
>> Hi,
>>
>> Does Moses server support lattice input?
>>
>>
>> Best,
>>
>> Hala
>>
>> _______________________________________________
>> 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/20140606/49e4f0b5/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 92, Issue 14
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 92, Issue 14"
Post a Comment