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: Generation step for factorized translation (Marco Damonte)
2. Re: Generation step for factorized translation (Hieu Hoang)
3. Re: Generation step for factorized translation (Marco Damonte)
----------------------------------------------------------------------
Message: 1
Date: Wed, 29 Jul 2015 12:26:23 +0000
From: Marco Damonte <mdtux89@gmail.com>
Subject: Re: [Moses-support] Generation step for factorized
translation
To: Hieu Hoang <hieuhoang@gmail.com>, "moses-support@mit.edu"
<moses-support@mit.edu>
Message-ID:
<CAD2JQQPNab4kNO_aQXzJnzgmcHi_No3T8L2pzBPA=+gdJpWDxw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Thank you! What do you mean by "mapping is too general"? Would you suggest
using the generation for coarse semantic classes (Supersenses)?
Marco
On Wed, 29 Jul 2015 1:21 pm Hieu Hoang <hieuhoang@gmail.com> wrote:
> This is my setup that generates target words from stems
> input-factors = word
> output-factors = word stem suffix
>
> alignment-factors = "word -> word"
> translation-factors = "word -> stem"
>
> reordering-factors = "word -> word"
> generation-factors = "stem -> word"
> decoding-steps = "t0, g0"
> you're not likely to get anything useful generating words from brown
> clusters - the mapping is just too general
>
> On 28/07/2015 20:46, Marco Damonte wrote:
>
> Hi,
>
> I'm using EMS and factorized translation. For instance, I have this
> setting:
>
> input-factors = word
> output-factors = word brown50
> alignment-factors = "word -> word"
> translation-factors = "word -> word+brown50"
> generation-factors = "brown50"
> reordering-factors = "word -> word"
> decoding-steps = "t0"
>
> that is, I have brown clusters as an output factor.
>
> Does someone can point me the proper way to add a generation step to
> create the surface word using the cluster factor?
>
> I tried:
> generation-factors = "brown50 -> word"
> but the experiment crashed durinh tuning
>
> Thanks in advance
> Marco
>
>
>
> _______________________________________________
> Moses-support mailing listMoses-support@mit.eduhttp://mailman.mit.edu/mailman/listinfo/moses-support
>
>
> --
> Hieu Hoang
> Researcher
> New York University, Abu Dhabihttp://www.hoang.co.uk/hieu
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150729/fcdff0bd/attachment-0001.htm
------------------------------
Message: 2
Date: Wed, 29 Jul 2015 16:30:44 +0400
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Generation step for factorized
translation
To: Marco Damonte <mdtux89@gmail.com>, "moses-support@mit.edu"
<moses-support@mit.edu>
Message-ID: <55B8C774.9050906@gmail.com>
Content-Type: text/plain; charset="utf-8"
all the generation step does is create the word factor, given the brown
cluster. If you only have 50 clusters, and say, all your verbs go into 1
custers, then the generation step would just create lots of verbs,
regardless of the source word.
Not only will this be a bad translation, you will prob run into
time/memory issues when trying to decode
On 29/07/2015 16:26, Marco Damonte wrote:
>
> Thank you! What do you mean by "mapping is too general"? Would you
> suggest using the generation for coarse semantic classes (Supersenses)?
>
> Marco
>
>
> On Wed, 29 Jul 2015 1:21 pm Hieu Hoang <hieuhoang@gmail.com
> <mailto:hieuhoang@gmail.com>> wrote:
>
> This is my setup that generates target words from stems
> input-factors = word
> output-factors = word stem suffix
>
> alignment-factors = "word -> word"
> translation-factors = "word -> stem"
>
> reordering-factors = "word -> word"
> generation-factors = "stem -> word"
> decoding-steps = "t0, g0"
> you're not likely to get anything useful generating words from
> brown clusters - the mapping is just too general
>
> On 28/07/2015 20:46, Marco Damonte wrote:
>> Hi,
>>
>> I'm using EMS and factorized translation. For instance, I have
>> this setting:
>>
>> input-factors = word
>> output-factors = word brown50
>> alignment-factors = "word -> word"
>> translation-factors = "word -> word+brown50"
>> generation-factors = "brown50"
>> reordering-factors = "word -> word"
>> decoding-steps = "t0"
>>
>> that is, I have brown clusters as an output factor.
>>
>> Does someone can point me the proper way to add a generation step
>> to create the surface word using the cluster factor?
>>
>> I tried:
>> generation-factors = "brown50 -> word"
>> but the experiment crashed durinh tuning
>>
>> Thanks in advance
>> Marco
>>
>>
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>
> --
> Hieu Hoang
> Researcher
> New York University, Abu Dhabi
> http://www.hoang.co.uk/hieu
>
--
Hieu Hoang
Researcher
New York University, Abu Dhabi
http://www.hoang.co.uk/hieu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150729/1f86df80/attachment-0001.htm
------------------------------
Message: 3
Date: Wed, 29 Jul 2015 12:33:23 +0000
From: Marco Damonte <mdtux89@gmail.com>
Subject: Re: [Moses-support] Generation step for factorized
translation
To: Hieu Hoang <hieuhoang@gmail.com>, "moses-support@mit.edu"
<moses-support@mit.edu>
Message-ID:
<CAD2JQQPeEd=tuqEFm4T5wK_R2AhgdkY6956vQVnFL+DWVqA-aA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Thank you. I wasn't thinking about it.
Marco
On Wed, 29 Jul 2015 1:30 pm Hieu Hoang <hieuhoang@gmail.com> wrote:
> all the generation step does is create the word factor, given the brown
> cluster. If you only have 50 clusters, and say, all your verbs go into 1
> custers, then the generation step would just create lots of verbs,
> regardless of the source word.
>
> Not only will this be a bad translation, you will prob run into
> time/memory issues when trying to decode
>
> On 29/07/2015 16:26, Marco Damonte wrote:
>
> Thank you! What do you mean by "mapping is too general"? Would you suggest
> using the generation for coarse semantic classes (Supersenses)?
>
> Marco
>
> On Wed, 29 Jul 2015 1:21 pm Hieu Hoang <hieuhoang@gmail.com> wrote:
>
>> This is my setup that generates target words from stems
>> input-factors = word
>> output-factors = word stem suffix
>>
>> alignment-factors = "word -> word"
>> translation-factors = "word -> stem"
>>
>> reordering-factors = "word -> word"
>> generation-factors = "stem -> word"
>> decoding-steps = "t0, g0"
>> you're not likely to get anything useful generating words from brown
>> clusters - the mapping is just too general
>>
>> On 28/07/2015 20:46, Marco Damonte wrote:
>>
>> Hi,
>>
>> I'm using EMS and factorized translation. For instance, I have this
>> setting:
>>
>> input-factors = word
>> output-factors = word brown50
>> alignment-factors = "word -> word"
>> translation-factors = "word -> word+brown50"
>> generation-factors = "brown50"
>> reordering-factors = "word -> word"
>> decoding-steps = "t0"
>>
>> that is, I have brown clusters as an output factor.
>>
>> Does someone can point me the proper way to add a generation step to
>> create the surface word using the cluster factor?
>>
>> I tried:
>> generation-factors = "brown50 -> word"
>> but the experiment crashed durinh tuning
>>
>> Thanks in advance
>> Marco
>>
>>
>>
>> _______________________________________________
>> Moses-support mailing listMoses-support@mit.eduhttp://mailman.mit.edu/mailman/listinfo/moses-support
>>
>>
>> --
>> Hieu Hoang
>> Researcher
>> New York University, Abu Dhabihttp://www.hoang.co.uk/hieu
>>
>>
> --
> Hieu Hoang
> Researcher
> New York University, Abu Dhabihttp://www.hoang.co.uk/hieu
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150729/0d79d805/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 105, Issue 64
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 105, Issue 64"
Post a Comment