Moses-support Digest, Vol 88, Issue 47

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: --activate-features in mert-moses.perl not working?
(Marcin Junczys-Dowmunt)
2. Re: --activate-features in mert-moses.perl not working?
(Marcin Junczys-Dowmunt)
3. Re: about-mosesv2-decoder-output (Hieu Hoang)
4. publication for "mert-moses.pl --pro-starting-point " ?
(Marcin Junczys-Dowmunt)
5. Re: publication for "mert-moses.pl --pro-starting-point " ?
(Barry Haddow)


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

Message: 1
Date: Sun, 23 Feb 2014 00:30:03 +0100
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: Re: [Moses-support] --activate-features in mert-moses.perl
not working?
To: moses-support@mit.edu
Message-ID: <530932FB.9060108@amu.edu.pl>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

BTW. "tuneable=false" seems to be ignored by Kenlm, works with other
features though.

W dniu 10.02.2014 21:15, Rico Sennrich pisze:
> Marcin Junczys-Dowmunt <junczys@...> writes:
>
>> Hi,
>> it seems --activate-features=STRING is not working in mert-moses.perl.
>> The script prints a message that the ignored features are not being
>> used, but then optimizes them anyway. I can see that the "enabled"
>> information in the feature data structure is not being used anywhere in
>> the script once it has been set (apart from printing the message).
> I don't know too much about the --activate-features option myself, but in
> recent Moses versions, you can add the option 'tuneable=false' to a feature
> function in the config. The effect is that the feature score(s) won't be
> reported to the n-best list, and MERT/MIRA/PRO won't even know that the
> feature exists. The weight from the original config will be used for all
> tuning iterations, and copied to the final config. You can now also specify
> the weight of sparse features in the config, and this will override the
> weight set in the weights file.
>
> best wishes,
> Rico
>
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support



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

Message: 2
Date: Sun, 23 Feb 2014 01:13:54 +0100
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: Re: [Moses-support] --activate-features in mert-moses.perl
not working?
To: moses-support@mit.edu
Message-ID: <53093D42.2020607@amu.edu.pl>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

And with "tuneable=false" it seems the features are being ignored during
decoding, I understand this should not be happening. I get much worse
translation results with an ini-file that has "tuneable=false" for all
features than with the same ini without the option. The translation is
also much faster with the options specified, so something is clearly not
being evaluated.

W dniu 23.02.2014 00:30, Marcin Junczys-Dowmunt pisze:
> BTW. "tuneable=false" seems to be ignored by Kenlm, works with other
> features though.
>
> W dniu 10.02.2014 21:15, Rico Sennrich pisze:
>> Marcin Junczys-Dowmunt <junczys@...> writes:
>>
>>> Hi,
>>> it seems --activate-features=STRING is not working in mert-moses.perl.
>>> The script prints a message that the ignored features are not being
>>> used, but then optimizes them anyway. I can see that the "enabled"
>>> information in the feature data structure is not being used anywhere in
>>> the script once it has been set (apart from printing the message).
>> I don't know too much about the --activate-features option myself, but in
>> recent Moses versions, you can add the option 'tuneable=false' to a feature
>> function in the config. The effect is that the feature score(s) won't be
>> reported to the n-best list, and MERT/MIRA/PRO won't even know that the
>> feature exists. The weight from the original config will be used for all
>> tuning iterations, and copied to the final config. You can now also specify
>> the weight of sparse features in the config, and this will override the
>> weight set in the weights file.
>>
>> best wishes,
>> Rico
>>
>>
>>
>> _______________________________________________
>> 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



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

Message: 3
Date: Sun, 23 Feb 2014 08:41:22 +0000
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] about-mosesv2-decoder-output
To: nadeem khan <nad_star06@yahoo.com>, moses-support
<moses-support@mit.edu>
Message-ID: <5309B432.3070508@gmail.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

when you use
-tt
the decoder outputs the segmentation and the score from each feature
function. If you just want the plain output don't use this option.

For your example
between 1998 and 2000 "|0-4,wa=,total=-6.00208, SRILM0= -17.297
Distortion0= 0 LexicalReordering0= -1.94591 0 0 0 0 0 WordPenalty0= -4 "

1. between 1998 and 2000
- the target oytput
2. 0-4
- the source range that was translated
3. wa=
- i guess this is word alignment
4. total=-6.00208
- the total score
5. SRILM0= -17.297
- the score for the language model
And so on


On 23/02/2014 01:24, nadeem khan wrote:
> -print-alignment-info -



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

Message: 4
Date: Sun, 23 Feb 2014 16:12:36 +0100
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: [Moses-support] publication for "mert-moses.pl
--pro-starting-point " ?
To: moses-support <moses-support@mit.edu>
Message-ID: <530A0FE4.6060908@amu.edu.pl>
Content-Type: text/plain; charset=UTF-8; format=flowed

Hi,
Is there a publication that describes the idea behind
"--pro-starting-point" option in mert-moses.pl? This seems to be working
really well for me.
Best,
Marcin


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

Message: 5
Date: Sun, 23 Feb 2014 16:55:22 +0000
From: Barry Haddow <bhaddow@staffmail.ed.ac.uk>
Subject: Re: [Moses-support] publication for "mert-moses.pl
--pro-starting-point " ?
To: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>, moses-support
<moses-support@mit.edu>
Message-ID: <530A27FA.1070003@staffmail.ed.ac.uk>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

Hi Marcin

It's mentioned here:
http://www.aclweb.org/anthology/W/W12/W12-3139.pdf
(section 4.2) but it's not something we spent much time experimenting with,

cheers - Barry

On 23/02/14 15:12, Marcin Junczys-Dowmunt wrote:
> Hi,
> Is there a publication that describes the idea behind
> "--pro-starting-point" option in mert-moses.pl? This seems to be working
> really well for me.
> Best,
> Marcin
> _______________________________________________
> 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


End of Moses-support Digest, Vol 88, Issue 47
*********************************************

Tweet