Moses-support Digest, Vol 91, 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. Call for Participation - Registration Open - The 37th Annual
ACM SIGIR 2014 conference - Gold Coast Australia - July 6-11
(Richi Nayak)
2. tuning tree-based models (Jorg Tiedemann)


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

Message: 1
Date: Mon, 19 May 2014 23:39:12 +0000
From: Richi Nayak <r.nayak@qut.edu.au>
Subject: [Moses-support] Call for Participation - Registration Open -
The 37th Annual ACM SIGIR 2014 conference - Gold Coast Australia -
July 6-11
To: Richi Nayak <r.nayak@qut.edu.au>
Message-ID:
<032189CFEE6B094A8CB9DB0838786ADF235BEA39@ex10mb1.qut.edu.au>
Content-Type: text/plain; charset="iso-8859-1"

Come and join us for the exciting SIGIR 2014 program of six days papers, posters, demonstrations, tutorials, workshops and social events, focused on research and development in the area of information retrieval.

http://sigir.org/sigir2014/index.php

It includes three SIGIR 2014 Plenaries:

ACM-W Athena Award Lecture: Putting Searchers into Search By Susan Dumais

Seeking Simplicity in Search User Interfaces By Marti Hearst

The data revolution: how companies are transforming with big data By Hugh E. Williams

The SIGIR 2014 registration is open (link below). The early bird deadline is 26 May 2014.

https://ei.eventinfotech.com.au/ei/rs.esp?id=1187&scriptid=HOME

Accommodation can also be reserved through the registration process, but of course the number
of reserved rooms in the conference hotel/s is limited. The weekend sees the Gold Coast Marathon
being run on 5/6 July and so accommodation should be arranged sooner rather than later.

Follow us on Social Media via Facebook and Twitter for latest updates and discussion:

https://www.facebook.com/SIGIR2014

https://twitter.com/intent/follow?original_referer=http%3A%2F%2Fsigir.org%2Fsigir2014%2Findex.php&screen_name=SIGIR2014&tw_p=followbutton&variant=2.0&xd_token=8d755076c852a8

______________________________________________
Dr Richi Nayak, Associate Professor
Higher Degree Research Director, School of Electrical Engineering and Computer Science
Science and Engineering Faculty| Queensland University of Technology |Brisbane, QLD 4001
Office: S1206 | Ph: 313 81976 | Fax: 313 89390 | Email: r.nayak@qut.edu.au?
Webpage: http://applieddatamining.info/





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

Message: 2
Date: Tue, 20 May 2014 16:40:22 +0200
From: Jorg Tiedemann <tiedeman@gmail.com>
Subject: [Moses-support] tuning tree-based models
To: moses-support <moses-support@mit.edu>
Message-ID: <0A9CA5FE-3EC0-4AFB-8322-96C12C32ACBF@gmail.com>
Content-Type: text/plain; charset=iso-8859-1


I'm struggling a bit with tuning my tree-based models. I try to run MERT on a syntax-to-string model but I have problems setting the flags for mert-moses.pl correctly. Now I tried something like

mert-moses.pl newstest2011.trees.es newstest2011.tok.true.fr moses_chart
es-fr/model/moses.ini \
--mertdir /path/to/mosesdecoder/bin \
--nbest 100 \
--working-dir es-fr/tuning \
--no-filter-phrase-table \
--inputtype 3 \
--rootdir /path/to/mosesdecoder/scripts

but after translating the devset in the first iteration my process stops with
Couldn't open es-fr/tuning/extractor.sh for writing: file or directory does not exist

The directory exists and the n-best list looks fine. Is there yet another flag that I have to add to the mert-moses call?

By the way, it took me some time to figure out that I have to set inputtype to 3 to make the system accept parsed input. Maybe someone could add this to the documentation (if it is correct like this anyway).

Another question: What would be the correct call to make mert-moses to filter the model before running? It doesn't work to add
'-Hierarchical' to the filtercmd as mert-moses then complains that the command is not found on the system (it doesn't remove flags before checking for existence). Or is it better to binarize the rule-tables anyway?

Thanks for your help!

J?rg









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

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


End of Moses-support Digest, Vol 91, Issue 25
*********************************************

Tweet