Moses-support Digest, Vol 92, Issue 25

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. CFP: Translating and the Computer Conference 2014 (Rohit Gupta)
2. A beginner question (Franz Bissinger)


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

Message: 1
Date: Wed, 11 Jun 2014 14:59:02 +0100
From: Rohit Gupta <enggrohitgupta@gmail.com>
Subject: [Moses-support] CFP: Translating and the Computer Conference
2014
To: moses-support@mit.edu, mt-list@eamt.org
Message-ID:
<CAB-CSF_o=ooTFOYywnOjfgC4qtW7vO64i7QPRhCryowbg3R4NA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

(Apologies for cross-posting. *Please, distribute it among potentially
interested colleagues*)


*Translating and the Computer Conference 2014*
A unique meeting point for experts in language research and technology
*27 ? 28 November 2014, London, UK*

*Call for abstracts*
First the Computer, then Internet and more recently the Cloud, are changing
and modelling expectations and processes in the Language and Localization
industry. These are accompanied by new requirements for Standards and
Intercompatibility. The digital age is modifying the concept of text and
quality. Content is a key item together with strings, chunks, segments and
words.
? How does this affect demand and supply of language services?
? What are the tools available to meet the new demands?
? What are the resources and how can they be managed in this evolving
context?
? How do these changes affect translators and other language professionals?
? What is the training necessary to deal with these new requirements?
*The Translating and the Computer Conference seeks submissions including,
but not limited to:*
? Terminology
? Translation technology (on and off-line)
- Memories
- Corpora (use of, data collection and structuring)
- Workflow (preprocessing, postprocessing and feedback loops,
progress tracking)
- Quality Assurance (revision aids, standards, processes and metrics)
? Fit for purpose translation (professional, human, automatic, gisting /
self-service)
? Machine Translation and Post Editing (technological advances, user
interfaces, real-world case studies)
? Collaborative and Crowd-sourced Translations
? Translation of real-time, user-generated content
? Translation of the spoken word (video, audio, interpreting)
? Standards (interoperability, return on investment, impact on quality)
*SUBMISSION GUIDELINES*
The conference committee seeks original unpublished papers on all aspects
of using computer hardware and software to assist in translation. Topics of
interest include, but are not limited to those listed above. Papers may
report on research, on commercial translation products as well as users and
actual implementations.
Authors are invited to submit an extended abstract of a maximum of 750
words of the paper they would like to present, together with a short 200
word abstract and short biography. While the extended abstract is limited
to 750 words (longer papers will NOT be considered), it should provide
sufficient information to allow evaluation of the submission by the
committee. The short abstracts of accepted papers will be used for online
programme and event advertising.
Abstracts must be submitted via the START conference submission system:
*https://www.softconf.com/e/tc2014*
<https://exchcas.unv.wlv.ac.uk/owa/redir.aspx?C=GZ-kJGqY0Um9YUJrRGGqAAO-EFXyWNEIRM4jfLAyodZAZ02yPV0fum3BaQWZjvJnZhcNMCyJdnA.&URL=http%3a%2f%2flistmanager.emeraldinsight.com%2ft%2f38301%2f27718893%2f103491317%2f7%2f>
Authors will be notified of acceptance or rejection of their submissions by
28 July 2014. Authors whose submissions are accepted for oral presentation
will subsequently have the option to submit a full paper for inclusion in
the conference proceedings, which will be produced on CD for conference
delegates. Speakers' final presentations must be submitted by 3 November
2014, in order to be included in the conference proceedings. Speakers will
be required to register for the conference and pay a reduced registration
fee.
*SCHEDULE*
*20 June 2014* - deadline for abstracts
*28 July 2014* - all authors notified of decisions
*3 November 2014* - speakers' full papers to be submitted
*14 November 2014* - speakers? presentations to be submitted
*27-28 November 2014* ? conference takes place in London
*Programme Chairs*
? Juliet Macan, Arancho Doc srl.
? Ruslan Mitkov, University of Wolverhampton
? Olaf-Michael Stefanov, United Nations (ret), JIAMCATT
? Jo?o Esteves-Ferreira, Tradulex, International Association for Quality
Translation
*Programme Committee*
? Alain D?silets, National Research Council of Canada (NRC)
? David Chambers, World Intellectual Property Organisation (ret)
? Gloria Corpas Pastor, University of Malaga
? David Filip, LRC, CNGL, LT-Web, University of Limerick
? Pamela Mayorca, Institute of Translating and Interpreting
? Paola Valli, University of Trieste
For more information, please go to the website
*www.translatingandthecomputer.com*
<https://exchcas.unv.wlv.ac.uk/owa/redir.aspx?C=GZ-kJGqY0Um9YUJrRGGqAAO-EFXyWNEIRM4jfLAyodZAZ02yPV0fum3BaQWZjvJnZhcNMCyJdnA.&URL=http%3a%2f%2flistmanager.emeraldinsight.com%2ft%2f38301%2f27718893%2f103491318%2f8%2f>
.
----------
Regards,
*Rohit Gupta*

*Marie Curie Early Stage Researcher, EXPERT Project*Research Group in
Computational Linguistics
Research Institute of Information and Language Processing
University of Wolverhampton
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140611/b20af4c5/attachment-0001.htm

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

Message: 2
Date: Wed, 11 Jun 2014 16:33:27 +0200
From: "Franz Bissinger" <franz@negation.info>
Subject: [Moses-support] A beginner question
To: <moses-support@mit.edu>
Cc: Franz Bissinger <franz@seschat.de>
Message-ID: <3AEF98A757C54CD98D7A0843BDDE20A5@Henna>
Content-Type: text/plain; charset="iso-8859-1"

Hello Everybody,

Before starting with my questions let me please introduce myself. My name is Franz Bissinger. I'm running a small localization company in Germany, Munich area. I'm familiar with all kinds of technical things related to the IT, but my major responsibility is to run my company and to do my daily localization work rather than to play with Linux and tools such as Moses. On the other side as it is usual in small companies I'm the guy dealing with all questions around hardware and software.

At the moment I'm trying to make my fist experiences with MT and especially with Moses. For doing so I configured an Ubuntu 12.04 server (8 Cores, 10 GB RAM), installed VirtualBox, downloaded the moses vm "debian 64-bit.ova" and imported it successfully to my server from where I run it in headless mode. I'm able to access the VM via a Remote Desktop Connection from my Windows 7 machine as well through ssh as via PUTTY. That's the background.

Today I tried for the first time to run the small sample found under "Phrase-based Tutorial" here http://www.statmt.org/moses/?n=Moses.Tutorial. Unfortunately, so far all my attempts to run moses with the sample 'das ist ein kleines haus' fails. This is my command line:



echo 'das ist ein kleines haus' | /opt/moses/bin/moses -f phrase-model/moses.ini > ../out



And this is what I'm getting out:

Defined parameters (per moses.ini or switch):
config: phrase-model/moses.ini
feature: KENLM name=LM factor=0 order=3 num-features=1 path=lm/europarl.srilm.gz Distortion WordPenalty UnknownWordPenalty PhraseDictionaryMemory input-factor=0 output-factor=0 path=phrase-model/phrase-table num-features=1 table-limit=10
input-factors: 0
mapping: T 0
n-best-list: nbest.txt 100
weight: WordPenalty0= 0 LM= 1 Distortion0= 1 PhraseDictionaryMemory0= 1
ERROR:Unknown parameter feature
ERROR:Unknown parameter weight
ERROR:No phrase translation table (ttable-file)



I do not really have an idea, what's wrong, Maybe the sample uses an version 1 moses.ini file. If that is true what would be the right command line if I'd use one of the europarl models (de-en) I downloaded from http://www.statmt.org/moses/RELEASE-2.1/models/ instead of the sample model?



I'm sorry to bother you with this kind of newbie questions, but unfortunately I'm not able to find any other helpful information.



Thanks a lot for your help in advance.



Best

Franz
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140611/0a713a26/attachment.htm

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

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


End of Moses-support Digest, Vol 92, Issue 25
*********************************************

Tweet