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: Baseline: Problem with tuned weights (Hieu Hoang)
2. Re: MT Marathon 2010 page hacked. (Ventsisav Zhechev)
3. Re: MT Marathon 2010 page hacked. (Marcin Junczys-Dowmunt)
4. Re: MT Marathon 2010 page hacked. (Ventsisav Zhechev)
----------------------------------------------------------------------
Message: 1
Date: Wed, 6 Jan 2016 17:33:22 +0000
From: Hieu Hoang <hieuhoang@gmail.com>
Subject: Re: [Moses-support] Baseline: Problem with tuned weights
To: Raphael H?ps <raphael.hoeps@gmx.net>, moses-support@mit.edu
Message-ID: <568D4FE2.7030109@gmail.com>
Content-Type: text/plain; charset="windows-1252"
are you sure you got the source and target side of the tuning set the
right way round?
And the tuning set must be tokenized and lowercase/truecased EXACTLY the
same way that you tokenized & lowercaseed/truecased the training data
On 04/01/16 17:16, Raphael H?ps wrote:
> Hello,
>
> I did the moses-baseline tutorial to train and tune and translation
> model for English to German. After finishing the system it seemed to
> work quite well at first but then I noticed that the tuning step
> seemed to actually having made my system worse! I really don't know
> what I did wrong. I sticked very close to the tutorial. Here is what I
> did in detail:
>
> 1. Training the TM to working/train/model.
> 2. Tuning with a corpus that is a cut-down version of news-test2008.
> The main result of this process are the weights of the new file
> mert-work/moses.ini, right?
> 3. Filtering of mert-work/moses.ini to a testing corpus (cut-down
> version of newstest2011).
> 4. Translating the testing corpus and calculating BLEU-score. I got a
> score of 7.42.
> 5. In a second test I used the default moses.ini file instead of the
> tuned one (and the same filtered and binarized model) and got a score
> of 8.22 on the same testing corpus!
>
> Something is probably wrong with the tuned moses.ini file. To find
> out, I translated the corpus that was used for tuning with both
> ini-files and calculated the scores:
> Untuned: 7.01
> Tuned: 6.70 (!)
>
> Now this is really odd! Furthermore in the tuned moses.ini file there
> is the line:
> # BLEU 0.0755253 on dev
> /home/rh/Studium/aktuell/LSS/moses/mosesdecoder/corpus/dev-small.en
> Why do I get a score of 6.7 instead? The files dev-small.en and
> dev-small.de where my tuning corpora.
>
> Do you have any idea, what I might have done wrong?
>
> For the tuning step, I used:
> cd ~/working
> nohup nice ~/mosesdecoder/scripts/training/mert-moses.pl \
> ~/corpus/dev-small.en ~/corpus/dev-small.de \
> ~/mosesdecoder/bin/moses train/model/moses.ini --mertdir
> ~/mosesdecoder/bin/ \ &> mert.out &
>
> I appended mert.log and the tune moses.ini file. Did anyone ever build
> a system for English to German and can say something about the trained
> weights in moses.ini? Do they seem okay?
>
> Thank you very much for your help!
> Greetings,
> Raphi
>
>
>
>
>
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
--
Hieu Hoang
http://www.hoang.co.uk/hieu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20160106/b408428e/attachment-0001.html
------------------------------
Message: 2
Date: Wed, 6 Jan 2016 10:05:52 -0800
From: Ventsisav Zhechev <contact@VentsislavZhechev.eu>
Subject: Re: [Moses-support] MT Marathon 2010 page hacked.
To: liling tan <alvations@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<D0EB6E7B-BC3C-4C49-A977-F9D9731C077A@VentsislavZhechev.eu>
Content-Type: text/plain; charset="utf-8"
Hi Liling,
I just got to the office and checked the page. I?m still looking after hosting the page and can confirm that http://mtmarathon2010.info <http://mtmarathon2010.info/> has not been hacked.
The presence of Russian text on the page is a side effect of the tool I used to build the website at the time and most probably got switched from English to Russian when I had to switch hosts around 2012. If I get a chance, I?ll try to find some time to fix that next week.
As for baiting users, I?m not quite sure what you mean by that. The link you provide is a genuine link to lecture material from the MT Marathon.
Cheers,
Ventzi
???????
Dr. Ventsislav Zhechev
Computational Linguist, Certified ScrumMaster?
http://VentsislavZhechev.eu <http://ventsislavzhechev.eu/>
> 6.01.2016 ?., ? 9:23, Philipp Koehn <phi@jhu.edu> ???????(?):
>
> Hi,
>
> I did not find anything hacked about the page, but it is maintained by Ventsislav Zhechev.
>
> -phi
>
> On Wed, Jan 6, 2016 at 8:07 AM, liling tan <alvations@gmail.com <mailto:alvations@gmail.com>> wrote:
> Dear Moses / MT Marathon organizers,
>
> I'm not sure whether this is the right place to report this.
>
> I was trying to retrieve a page from MT Marathon 2010 and it seems like a Russian hacker hacked the page and took over it: http://www.mtmarathon2010.info/ <http://www.mtmarathon2010.info/> (see the lower right corner).
>
> And it's using the high google pagerank index to bait people onto pages like: http://www.mtmarathon2010.info/web/Program_files/survey.pdf <http://www.mtmarathon2010.info/web/Program_files/survey.pdf>
>
> Regards,
> Liling
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
> http://mailman.mit.edu/mailman/listinfo/moses-support <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/20160106/209780e6/attachment-0001.html
------------------------------
Message: 3
Date: Wed, 6 Jan 2016 19:14:58 +0100
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: Re: [Moses-support] MT Marathon 2010 page hacked.
To: moses-support@mit.edu
Message-ID: <568D59A2.200@amu.edu.pl>
Content-Type: text/plain; charset=windows-1252; format=flowed
>
> As for baiting users, I?m not quite sure what you mean by that. The
> link you provide is a genuine link to lecture material from the MT
> Marathon.
>
Totally a bait. It's named "survey" and all that so-called MT stuff
looks very fishy to me.
------------------------------
Message: 4
Date: Wed, 6 Jan 2016 10:35:21 -0800
From: Ventsisav Zhechev <contact@VentsislavZhechev.eu>
Subject: Re: [Moses-support] MT Marathon 2010 page hacked.
To: liling tan <alvations@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<D655BC3E-B0E4-450F-8302-CAD7595818FC@VentsislavZhechev.eu>
Content-Type: text/plain; charset="utf-8"
Hi Liling,
The problem seems to be somewhere on your side, i.e. your computer or network. The MT Marathon 2010 page works fine for me and is retrieving the correct documents both on my company?s network and via my phone?s network.
Can anyone else confirm getting fraudulent content from the http://mtmarathon2010.info <http://mtmarathon2010.info/> website?
Cheers,
Ventzi
???????
Dr. Ventsislav Zhechev
Computational Linguist, Certified ScrumMaster?
http://VentsislavZhechev.eu <http://ventsislavzhechev.eu/>
> 6.01.2016 ?., ? 10:26, liling tan <alvations@gmail.com <mailto:alvations@gmail.com>> ???????(?):
>
> Dear Moses dev and MT Marathon organizer,
>
> Whoops, I might have been mistaken. I'm not sure what happened but there's also this page: http://www.mtmarathon2010.info/web/Program_files/art-tyers-et-al.pdf <http://www.mtmarathon2010.info/web/Program_files/art-tyers-et-al.pdf> that leads to the screen shot.
>
>
> Regards,
> Liling
>
> On Wed, Jan 6, 2016 at 7:05 PM, Ventsisav Zhechev <contact@ventsislavzhechev.eu <mailto:contact@ventsislavzhechev.eu>> wrote:
> Hi Liling,
> I just got to the office and checked the page. I?m still looking after hosting the page and can confirm that http://mtmarathon2010.info <http://mtmarathon2010.info/> has not been hacked.
>
> The presence of Russian text on the page is a side effect of the tool I used to build the website at the time and most probably got switched from English to Russian when I had to switch hosts around 2012. If I get a chance, I?ll try to find some time to fix that next week.
>
>
> As for baiting users, I?m not quite sure what you mean by that. The link you provide is a genuine link to lecture material from the MT Marathon.
>
>
> Cheers,
>
> Ventzi
>
> ???????
> Dr. Ventsislav Zhechev
> Computational Linguist, Certified ScrumMaster?
>
> http://VentsislavZhechev.eu <http://ventsislavzhechev.eu/>
>
>
>> 6.01.2016 ?., ? 9:23, Philipp Koehn <phi@jhu.edu <mailto:phi@jhu.edu>> ???????(?):
>>
>> Hi,
>>
>> I did not find anything hacked about the page, but it is maintained by Ventsislav Zhechev.
>>
>> -phi
>>
>> On Wed, Jan 6, 2016 at 8:07 AM, liling tan <alvations@gmail.com <mailto:alvations@gmail.com>> wrote:
>> Dear Moses / MT Marathon organizers,
>>
>> I'm not sure whether this is the right place to report this.
>>
>> I was trying to retrieve a page from MT Marathon 2010 and it seems like a Russian hacker hacked the page and took over it: http://www.mtmarathon2010.info/ <http://www.mtmarathon2010.info/> (see the lower right corner).
>>
>> And it's using the high google pagerank index to bait people onto pages like: http://www.mtmarathon2010.info/web/Program_files/survey.pdf <http://www.mtmarathon2010.info/web/Program_files/survey.pdf>
>>
>> Regards,
>> Liling
>>
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu <mailto:Moses-support@mit.edu>
>> http://mailman.mit.edu/mailman/listinfo/moses-support <http://mailman.mit.edu/mailman/listinfo/moses-support>
>>
>>
>
>
> <Screenshot from 2016-01-06 19:25:37.png>
Ventzi
???????
Dr. Ventsislav Zhechev
Computational Linguist, Certified ScrumMaster?
http://VentsislavZhechev.eu <http://ventsislavzhechev.eu/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20160106/7fd38f5b/attachment.html
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 111, Issue 5
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 111, Issue 5"
Post a Comment