Moses-support Digest, Vol 86, Issue 79

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. Multiple Translation Tables and Back-off Models - changing
moses.ini according to specification (Ivan Dun?er)
2. Re: Multiple Translation Tables and Back-off Models -
changing moses.ini according to specification (Hieu Hoang)
3. problem in tokenization (Arththika Paramanathan)


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

Message: 1
Date: Sat, 28 Dec 2013 21:21:05 +0100
From: Ivan Dun?er <ivandunder@gmail.com>
Subject: [Moses-support] Multiple Translation Tables and Back-off
Models - changing moses.ini according to specification
To: moses-support@mit.edu
Message-ID:
<CAP1sQ+ZsyE1CsUV7C1ASbs4sO51g0oEL0Txn3KRSbZ1T4Aau5g@mail.gmail.com>
Content-Type: text/plain; charset=ISO-8859-1

Hi all and good evening,

I would like to experiment with "Multiple Translation Tables and
Back-off Models"
(http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc20) and the
manual states that I need to specify the translation tables in the
moses.ini as follows:

[feature]
PhraseDictionaryMemory path=/my-dir/table1 ...
PhraseDictionaryMemory path=/my-dir/table2 ...

Can I use PhraseDictionaryBinary instead, in order to call binarised versions?

Could someone please send me a modified "moses.ini" file (containing
the mentioned feature, weights and mapping sections and
decoding-graph-back-off), so I can take a look for more details and
adapt it eventually?

Thank you very much and best regards,
Ivan Dunder


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

Message: 2
Date: Sun, 29 Dec 2013 15:03:04 +0000
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Multiple Translation Tables and Back-off
Models - changing moses.ini according to specification
To: Ivan Dun?er <ivandunder@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbi7j3S1cp84rHZ+g0+5q+cwCdqW3TKdSyAgE98XKv-SLw@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

On 28 December 2013 20:21, Ivan Dun?er <ivandunder@gmail.com> wrote:

> Hi all and good evening,
>
> I would like to experiment with "Multiple Translation Tables and
> Back-off Models"
> (http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc20) and the
> manual states that I need to specify the translation tables in the
> moses.ini as follows:
>
> [feature]
> PhraseDictionaryMemory path=/my-dir/table1 ...
> PhraseDictionaryMemory path=/my-dir/table2 ...
>
> Can I use PhraseDictionaryBinary instead, in order to call binarised
> versions?
>

yes

>
> Could someone please send me a modified "moses.ini" file (containing
> the mentioned feature, weights and mapping sections and
> decoding-graph-back-off), so I can take a look for more details and
> adapt it eventually?
>

please see attached. There is a main phrase-table (TranslationModel0).
There is also a transliteration phrase-table (translit) which the decoder
uses as a backoff if the word isn't found in the TranslationModel0

>
> Thank you very much and best regards,
> Ivan Dunder
> _______________________________________________
> 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/20131229/3313224e/attachment-0001.htm
-------------- next part --------------
A non-text attachment was scrubbed...
Name: moses.translit.ini
Type: application/octet-stream
Size: 2408 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20131229/3313224e/attachment-0001.obj

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

Message: 3
Date: Sun, 29 Dec 2013 22:00:48 +0530
From: Arththika Paramanathan <arthiparamanathan@gmail.com>
Subject: [Moses-support] problem in tokenization
To: moses-support <moses-support@mit.edu>
Message-ID:
<CAJSfqEw4=j-WzzafyhcYy6H5VeowMMMLCjcisP4X8Ut5xfHomg@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

Hi,
I have a problem in tokenization step. I created a nonbreaking_prefix.ta
file for Tamil. So, there wasn't show any error message. But, I faced a
problem in tokenized file because of the characer called zero with joiner
in Tamil. Where I want to define this character(in tokenizer.perl?)



--
regards,
P.Arththika
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20131229/75080048/attachment-0001.htm

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

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


End of Moses-support Digest, Vol 86, Issue 79
*********************************************

Tweet