Moses-support Digest, Vol 93, Issue 37

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: Issues with Incremental retraining using Moses (Hieu Hoang)
2. PhrasePenalty and several phrase tables (Marcin Junczys-Dowmunt)
3. Re: PhrasePenalty and several phrase tables (Hieu Hoang)
4. Coling 2014 Programme (COLING 2014 - Registration)


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

Message: 1
Date: Tue, 29 Jul 2014 00:35:26 +0100
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Issues with Incremental retraining using
Moses
To: Sandipan Dandapat <sandipandandapat@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbjCgETPK-p_845w51DcA2S+OYiM92yzDU0qOpTu3ZxiVg@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

I'm not an expert on the dynamic suffix array so the following advise may
the incorrect.

On 28 July 2014 07:51, Sandipan Dandapat <sandipandandapat@gmail.com> wrote:

> Hi,
> I am trying to use Moses Incremental Retraining as described in
> http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc33
>
> I have two doubts:
>
> 1. I am able to generate the new-alignment-file using additional data on
> top of previously used data. Once the new alignment file is generated, the
> page says to update the model. I am unable to understand how to use the
> same during decoding? Can you please help me to understand how can I
> proceed once my new-allignment file is generated?
>
You issue a xmlrpc command to the moses server. Please see the script
contrib/server/update.py


> 2. What is happening when we are updating the moses.ini file using
>
> PhraseDictionaryDynSuffixArray source=<path-to-source-corpus> target=<path-to-target-corpus> alignment=<path-to-alignments>
>
> I am unable to see any reference to this updated moses.ini file in the
> rest of the section.
>
The moses.ini file isn't updated. The suffix array is updated

>
> Thanks and regards,
> sandipan
> --------------------------------
> Sandipan Dandapat
> Postdoctoral Researcher
> CNGL, School of Computing
> Dublin City University
> Google Scholar Profile:
> http://scholar.google.co.in/citations?user=DWD_FiQAAAAJ&hl=en
>
> _______________________________________________
> 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/20140729/eda01624/attachment-0001.htm

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

Message: 2
Date: Tue, 29 Jul 2014 14:29:07 +0200
From: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Subject: [Moses-support] PhrasePenalty and several phrase tables
To: moses-support <moses-support@mit.edu>
Message-ID: <53D79393.4080800@amu.edu.pl>
Content-Type: text/plain; charset=UTF-8; format=flowed

Hi,
Is the PhrasePenalty feature now a global feature that counts the number
of used phrases for all phrase tables cumulatively? Is there a way to
have a PhrasePenalty feature per phrase table other than reinserting
exp(1) to the phrase table again? I would imagine that in a multiple
phrase table scenario the phrase penalty per phrase table is quite
distinctive...

Best,
Marcin


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

Message: 3
Date: Tue, 29 Jul 2014 15:19:41 +0100
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] PhrasePenalty and several phrase tables
To: Marcin Junczys-Dowmunt <junczys@amu.edu.pl>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbhnEdNWE_jpDWE1dX5OJys2PhifgMvcbCHCkesdsjz83g@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

yes, the PhrasePenalty is global, there's no way to change that. To add the
exp(1) back into the phrase-table, run consolidate with
--PhraseCount


On 29 July 2014 13:29, Marcin Junczys-Dowmunt <junczys@amu.edu.pl> wrote:

> Hi,
> Is the PhrasePenalty feature now a global feature that counts the number
> of used phrases for all phrase tables cumulatively? Is there a way to
> have a PhrasePenalty feature per phrase table other than reinserting
> exp(1) to the phrase table again? I would imagine that in a multiple
> phrase table scenario the phrase penalty per phrase table is quite
> distinctive...
>
> Best,
> Marcin
> _______________________________________________
> 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/20140729/0146c9d6/attachment-0001.htm

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

Message: 4
Date: Tue, 29 Jul 2014 14:34:38 +0000
From: COLING 2014 - Registration <COLING2014Reg@keynotepco.ie>
Subject: [Moses-support] Coling 2014 Programme
To: COLING 2014 - Registration <COLING2014Reg@keynotepco.ie>
Message-ID:
<fc103823450d420ba6815e15a66e0141@AM3PR03MB546.eurprd03.prod.outlook.com>

Content-Type: text/plain; charset="us-ascii"

Trouble viewing this email? View in Browser<http://www.coling-2014.org/programme_email.html>


[http://www.coling-2014.org/img/email_header.png]


[http://www.coling-2014.org/img/coling_logo.png]<http://www.coling-2014.org/index.php>


[http://www.coling-2014.org/img/email_1.jpg]


Less that 1 month left to register!
Click here to Register<http://www.coling-2014.org/registration.php>
Click for details on Main Conference<http://www.coling-2014.org/schedule.php>,
1 or 2 day Workshops<http://www.coling-2014.org/workshops.php> and half day Tutorials<http://www.coling-2014.org/tutorials.php> and Demos.<http://www.coling-2014.org/accepted-demos.php>
Not forgetting the Excursion Day!<http://www.coling-2014.org/excursion.php>


Conference Programme





Monday - August 25th<http://www.coling-2014.org/schedule/monday25august.php>

09:00 - 10:15

Invited Speaker: Mary Harper, IARPA
Learning from 26 languages: Program Management and Science in the Babel Program

10:45 - 12:25

Modeling of Discourse and Dialogue I

10:45 - 12:25

Sentiment Analysis, Opinion Mining and Social Media I

10:45 - 12:25

Information Retrieval and Question Answering

10:45 - 12:25

Machine Learning for CL and NLP

15:45 - 17:25

Modeling of Discourse and Dialogue II

15:45 - 17:25

Sentiment Analysis, Opinion Mining and Social Media III

15:45 - 17:25

Semantic Processing, Distributional Semantics and Compositional Semantics I

15:45 - 17:25

Software, Tools

Tuesday - August 26th<http://www.coling-2014.org/schedule/tuesday26august.php>

09:00 - 10:15

Invited Speaker: Ted Gibson, MIT
Language for communication: Language as rational inference

10:45 - 12:25

Syntax, grammar induction, syntactic and semantic parsing I

10:45 - 12:25

Sentiment Analysis, Opinion Mining and Social Media III

10:45 - 12:25

Applications I

10:45 - 12:25

Modeling of Discourse and Dialogue III

15:45 - 17:25

Syntax, grammar induction, syntactic and semantic parsing II

15:45 - 17:25

Semantic Processing, Distributional Semantics and Compositional Semantics II

15:45 - 17:25

Applications II

15:45 - 17:25

Language Resources

Wednesday - August 27th<http://www.coling-2014.org/schedule.php>

09:00 - 10:15

Exursion Day

Thursday - August 28th<http://www.coling-2014.org/schedule/thursday28august.php>

09:00 - 10:15

Invited Speaker: Qun Liu, CNGL/DCU
Annotation Adaptation and Language Adaptation in NLP

10:45 - 12:25

IE/database linking I

10:45 - 12:25

Lexical Semantics and Ontologies I

10:45 - 12:25

Natural Language Generation and Summarization I

10:45 - 12:25

Modeling of Discourse and Dialogue IV and Multimodal Processing

14:00 - 15:15

Semantic Processing, Distributional Semantics and Compositional Semantics III

14:00 - 15:15

Morphology, word segmentation, tagging and chunking I

14:00 - 15:15

Speech Recognition, Text-To-Speech, Spoken Language Understanding

14:00 - 15:15

Lesser Resourced Languages

15:45 - 17:25

Syntax, grammar induction, syntactic and semantic parsing III

15:45 - 17:25

Machine Translation I

15:45 - 17:25

Linguistic and Cognitive Issues in CL and NLP I

15:45 - 17:25

Natural Language Generation and Summarization II and Paraphrasing

Friday - August 29th<http://www.coling-2014.org/schedule/friday29august.php>

09:00 - 10:15

Invited Speaker: Martin Kay, XEROX
Does a Computational Linguist have to be a Linguist?

10:45 - 12:25

Machine Translation II

10:45 - 12:25

IE/database linking II

10:45 - 12:25

Linguistic and Cognitive Issues in CL and NLP II

10:45 - 12:25

Lexical Semantics and Ontologies II

14:00 - 15:15

Machine Translation III

14:00 - 15:15

Lexical Semantics and Ontologies III

14:00 - 15:15

IE/database linking III

14:00 - 15:15

Morphology, word segmentation, tagging and chunking II

15:45 - 17:25

Best Paper Talk and Closing

The conference committee and organisers take no responsibility for changes or inaccuracies to the conference programme. The above programme is subject to change.


Accommodation
Don't forget to book your accommodation at time of registering. Rooms are limited on campus and early booking is advisable!
To view accommodation options click here<http://www.coling-2014.org/accommodation.php>. Just book on the registration form at the same time as your registration.


Our Sponsors

[http://www.coling-2014.org/img/sponsors_email.jpg]<http://www.coling-2014.org/sponsors.php>


Ireland Inspires!
Click here to see the Ireland Inspires Video<https://www.youtube.com/watch?v=9wmIZEl1nSo&feature=youtu.be>





Coling 2014

www.coling2014.org<http://www.coling-2014.org/index.php> | coling2014reg@keynotepco.ie | View in Browser<http://www.coling-2014.org/programme_email.html>



-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140729/03c64142/attachment.htm

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

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


End of Moses-support Digest, Vol 93, Issue 37
*********************************************

0 Response to "Moses-support Digest, Vol 93, Issue 37"

Post a Comment