Moses-support Digest, Vol 107, Issue 30

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: Error (Kenneth Heafield)
2. How to Divide Corpus (Asad A.Malik)


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

Message: 1
Date: Fri, 11 Sep 2015 14:29:01 +0200
From: Kenneth Heafield <moses@kheafield.com>
Subject: Re: [Moses-support] Error
To: moses-support@mit.edu
Message-ID: <55F2C90D.7020802@kheafield.com>
Content-Type: text/plain; charset=windows-1252

Hi,

None of the words is in the vocabulary. Which suggests you did not
properly train the model. However that part was not visible in the
screenshot.

Kenneth

On 09/11/15 14:20, fatma elzahraa Eltaher wrote:
> Dear All,
>
> I try to test Language model with two sentences ( I can do that , I
> can dose that ) but the output was the same. I expected that the
> probability of the correct sentences will be better.could you tell me
> where is the problem.
> I attached image which clear the output.
>
> note: I use the English data in
> (http://www.statmt.org/wmt13/training-parallel-nc-v8.tgz)
>
> thank you,
>
>
>
> Fatma El-Zahraa El -Taher
>
> Teaching Assistant at Computer & System department
>
> Faculty of Engineering, Azhar University
>
> Email : fatmaeltaher@gmail.com <mailto:fatmaeltaher@gmail.com>
> mobile: +201141600434
>
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support



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

Message: 2
Date: Fri, 11 Sep 2015 15:08:55 +0000 (UTC)
From: "Asad A.Malik" <asad_12204@yahoo.com>
Subject: [Moses-support] How to Divide Corpus
To: Moses-support <moses-support@mit.edu>
Message-ID:
<1949622555.1079148.1441984135294.JavaMail.yahoo@mail.yahoo.com>
Content-Type: text/plain; charset="utf-8"

Hi All,
I have parallel corpus of almost 80,000 words. I wanted to divide it in to training, tuning and testing corpus. Kindly guide me that how should I divide my corpus??
Also the text in one corpus in not properly tokenized. As I am using urdu then there are some words in which there is space in one single word. Kindly guide that how can I tokenize this type of corpus??--

Kind Regards,

Mr. Asad Abdul Malik

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150911/c20fa983/attachment-0001.html

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

_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support


End of Moses-support Digest, Vol 107, Issue 30
**********************************************

Tweet