Moses-support Digest, Vol 94, Issue 20

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. Call for Papers and Participation: The Fifth Swedish Language
Technology Conference (SLTC-14) (Jorg Tiedemann)
2. Re: Problem at a training stage - linguistic model not
correctly trained (Hieu Hoang)
3. Re: Questions on the system. (Hieu Hoang)


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

Message: 1
Date: Fri, 15 Aug 2014 09:58:18 +0200
From: Jorg Tiedemann <tiedeman@gmail.com>
Subject: [Moses-support] Call for Papers and Participation: The Fifth
Swedish Language Technology Conference (SLTC-14)
To: moses-support <moses-support@mit.edu>
Message-ID: <5FE90B18-A498-4640-BF3A-02FB120C8808@gmail.com>
Content-Type: text/plain; charset=windows-1252

The Fifth Swedish Language Technology Conference (SLTC-14)
http://www2.lingfil.uu.se/SLTC2014
Uppsala, Sweden, November 13-14, 2014

Submissions: https://www.easychair.org/conferences/?conf=sltc2014
Registration: http://www2.lingfil.uu.se/SLTC2014/registration.html

Invited talks by:

- Stephen Clark, University of Cambridge
- Mirella Lapata, University of Edinburgh
- Slav Petrov, Google

Workshops:

WS1: The first national SWE-CLARIN workshop: LT-based e-HSS in Sweden ? taking stock and looking ahead
WS2: 1st Nordic workshop on evaluation of spellchecking and proofing tools (NorWEST2014)
WS3: 3rd workshop on NLP for computer-assisted language learning
WS4: Workshop on Action, Perception and Language (APL2)

Call for papers:

Papers are invited on all aspects of language technology, including natural language processing, speech technology, and relevant neighboring areas. Papers can describe completed or ongoing research, as well as practical applications of language technology, and may be combined with system demonstrations.

Format: Papers will be presented at the conference either as posters or as oral presentations and will be made available on the conference web page as extended abstracts.

Submission: Papers should be submitted as extended abstracts (max. 2 pages) using the style files provided. Papers must be submitted via the online paper submission system: https://www.easychair.org/conferences/?conf=sltc2014

Deadline: The deadline for submission is September 1, 2014.

Review: Papers will be reviewed by the program committee. Authors will be notified September 22, 2014.

URL: http://www2.lingfil.uu.se/SLTC2014/call.html


Contact:
Scientific issues: sltc2014@lingfil.uu.se
Practical issues: sltc2014@akademikonferens.uu.se

Organising Committee:
Joakim Nivre (chair)
Mats Dahll?f
Beata Megyesi
Sara Stymne
J?rg Tiedemann




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

Message: 2
Date: Fri, 15 Aug 2014 10:57:03 +0100
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Problem at a training stage - linguistic
model not correctly trained
To: "Radian's Translation Bureau" <info@radians.net>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbg-RJ94u_9_68kcEAWtEJVXrgwS_pFWA3Wt4T6Sa+e=JQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

What is the exact command you ran when you got this error?

Also, may might want to try using lmplz from KenLM to train your language
model. It is documented here:

http://www.statmt.org/moses/?n=FactoredTraining.BuildingLanguageModel#ntoc20


On 11 August 2014 18:33, Radian Yazynin <info@radians.net> wrote:

> Dear Support staff members,
>
> I will appreciate if you help me with one issue.
> These are my first steps...
> I am trying out a Moses-For-Mere-Mortals package (Moses + IRSTLM + RandLM
> + MGIZA)
> in Ubuntu 14.04.1 64bit.
> Compilation resulted in one error only: MGIZA didn't install correctly.
> After that I downloaded MGIZA as suggested at http://www.statmt.org/moses/
> and installed it separately
> into the folder where the erroneous MGIZA existed (in order to run the
> scripts correctly).
> The preparatory step with test files in PT and EN (as included) was OK.
> Now that I try to use the test corpora with ./train-1.11 the training
> procedure starts alright but
> after about 10 minutes terminates with the following:
>
> compile-lm: lmtable.cpp:237: int parseline(std: :istream&, int,
> ngram&, float&, float&): Assertion 'howmany == (Order+ 1) || ho
> wmany == (Order + )'' failed.
> Aborted (core dumped)
> *************** Writing training summary
> Linguistic model not correctly trained. Exiting...
>
> Thanks so much for you help!
>
> Kind regards
>
>
> *Radian Yazynin Tula, Russia*
>
> _______________________________________________
> 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/20140815/38725d36/attachment-0001.htm

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

Message: 3
Date: Fri, 15 Aug 2014 11:01:01 +0100
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Questions on the system.
To: Arjun Bhalla <arjunbhalla675@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbjp=+ft0noyRGeoJzfh_btZc9GFNfOEkB+z3oMp-4MfJQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

you should do a tutorial on Moses before attempting to integrate it into
your app. There is a step-by-step guide here:
http://www.statmt.org/moses/?n=Moses.Baseline


On 10 August 2014 05:27, Arjun Bhalla <arjunbhalla675@gmail.com> wrote:

> Hi,
>
> I've already downloaded it to my machine and I can currently run
> translations through the GUI. But I want to use this in a Python app. This
> is a panel-polling app for a networking company that holds conferences on
> various topics in the tech field, and it's meant to gather questions from
> guests in real-time and produce good translations for those questions in as
> many languages as possible. Right now I only know how to upload a
> translation model to the GUI and type in sentences to translate. I need to
> be able to use this translation system and code it into this Python app. I
> have no idea where to begin. What code do I write in my Python program to
> call Moses?
>
> Also I have a more immediate issue: I'm trying to run Moses translations
> on the command line. I'm running on Windows 7 and I found this page that is
> helping me a little
> https://www.mail-archive.com/moses-support@mit.edu/msg10003.html.
>
> That page says I need preprocessing steps with tokenizer.exe. When I type
> in what it says, it just shows me a cursor where I have to type in input,
> and once I do, it just echoes the input back to me and the program doesn't
> end unless I force-crash it. Was there something special I needed to know
> about how to use tokenizer.exe?
>
> Thanks a lot,
>
> Arjun Bhalla
>
> _______________________________________________
> 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/20140815/8db9c65d/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 94, Issue 20
*********************************************

Tweet