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. NoDaLiDa 2015: Call for Papers (Be?ta Megyesi)
2. about CCG factored-based model (Eng HAR)
3. Re: about CCG factored-based model (Philipp Koehn)
4. problem with loading binarized rule -table (Arefeh Kazemi)
----------------------------------------------------------------------
Message: 1
Date: Wed, 17 Dec 2014 09:53:36 +0000
From: Be?ta Megyesi <Beata.Megyesi@lingfil.uu.se>
Subject: [Moses-support] NoDaLiDa 2015: Call for Papers
To: ACL 2014 <acl@aclweb.org>, "<corpora@uib.no>" <corpora@uib.no>,
"<elsnet-list@elsnet.org>" <elsnet-list@elsnet.org>,
"<nodali@helsinki.fi>" <nodali@helsinki.fi>, "<nordlingnet@uib.no>"
<nordlingnet@uib.no>, "<nealt-members@iln.uio.no>"
<nealt-members@iln.uio.no>, "<alla@gslt.hum.gu.se>"
<alla@gslt.hum.gu.se>, "<hpsg-l@mailman.stanford.edu>"
<hpsg-l@mailman.stanford.edu>, "<lfg@listserv.linguistlist.org>"
<lfg@listserv.linguistlist.org>, "<moses-support@mit.edu>"
<moses-support@mit.edu>, "<mt-list@eamt.org>" <mt-list@eamt.org>
Cc: "nodalida15@stp.lingfil.uu.se" <nodalida15@stp.lingfil.uu.se>
Message-ID: <11D331FB-297A-4BEB-B29E-F36B4FE5C7D2@lingfil.uu.se>
Content-Type: text/plain; charset="utf-8"
[with apologies for cross-posting]
20th Nordic Conference on Computational Linguistics (NoDaLiDa)
Monday, May 11, to Wednesday, May 13, 2015
Institute of the Lithuanian Language, Vilnius, Lithuania
http://lki.lt/nodalida/
https://easychair.org/conferences/?conf=nodalida15
CALL FOR PAPERS
The Northern European Association for Language Technology (NEALT)
invites submissions to its bi-annual conference on human language and
speech technologies. NoDaLiDa 2015 will be held between May 11 and May
13, 2015, on the campus of the University of Vilnius, Lithuania. Please
mark your calendars.
CONFERENCE HIGHLIGHTS
As part of the main conference, there will be three invited keynotes:
+Kevin Knight, ISI, University of Southern California, USA
+Catherine Pelachaud, CNRS, TELECOM Paris Tech, France
+Sebastian Riedel, University College London, UK
Preceding the main conference, on Monday, May 11, there will be four
topical workshops:
+ 4th workshop on NLP for Computer Assisted Language Learning (NLP4CALL)
+ Semantic resources and semantic annotation for Natural Language Processing and the Digital Humanities
+ Innovative Corpus Query and Visualization Tools
+ Constraint Grammar - Methods, Tools and Applications
Workshops will issue individual call for papers in mid-January and will
have a closing date for submissions in March.
SUBMISSIONS
NoDaLiDa addresses all aspects of speech recognition and synthesis,
natural language processing, and computational linguistics, including
work in closely related neighbouring disciplines (such as, for example,
linguistics or psychology) that is sufficiently formalized or applied
to bear relevance to speech and language technologies.
We invite paper submissions in three distinct tracks:
+ regular papers on substantial, original, and unpublished research,
including empirical evaluation results, where appropriate;
+ short papers on smaller, focused contributions, work in progress,
negative results, surveys, or opinion pieces; and
+ student papers on completed or ongoing work, where at least the first
author is a Master or PhD student.
There will be a fourth track for system demonstrations, with a separate
call for papers and submission deadline in March 23, 2015.
Papers accepted for presentation at the conference will be included in
the NoDaLiDa 2015 proceedings, which is published as part of the NEALT
Proceedings Series by Link?ping University Electronic Press.
The proceedings will be publicly available in the ACL Anthology:
http://aclweb.org/anthology-new/
SCHEDULE
+ Monday, January 19, 2015: Submission of Papers
+ Monday, March 16, 2015: Notification of Acceptance
+ Monday, March 30, 2015: Camera-Ready Manuscripts
+ Monday, May 11, 2015: Pre-Conference Workshops
+ Tuesday & Wednesday, May 12 & 13, 2015: Main Conference
SUBMISSION FORMATS
All submissions must follow the NoDaLiDa 2015 style files, which are
available for LaTeX (preferred) or MS Word and can be
retrieved from the following address:
http://stp.lingfil.uu.se/~bea/nodalida15/
Submissions must be anonymous, i.e. not reveal author(s) on the title
page or through self-references. Papers must be submitted digitally,
in PDF, and uploaded through the on-line conference system. Paper
submissions that violate either of these requirements will be returned
without review.
The page limits for submissions are: up to eight pages for regular
papers, up to four pages for short papers, and up to six pages for
student papers. For all three submission types, these page limits do
/not/ include additional pages with bibliographic references.
SUBMISSION MANAGEMENT
Submissions to the conference must be uploaded electronically, obeying
the above requirements and no later than (end of day, world-wide):
Monday, January 19, 2015
NoDaLiDa 2015 utilizes the EasyChair conference management system for
submission, reviewing, and preparation of proceedings. Submission for
the conference is now open at:
https://easychair.org/conferences/?conf=nodalida15
PROGRAMME COMMITTEE
Reviewing of submissions and selection of the conference programme will
be managed by the NoDaLiDa 2015 Programme Committee. All submissions
will receive three double-blind reviews by experts in the field.
+ Be?ta Megyesi (program chair), Uppsala University, Sweden
+ Filip Ginter, University of Turku, Finland
+ Kristiina Jokinen, University of Helsinki, Finland
+ Arne J?nsson, Link?ping University, Sweden
+ Violeta Meili?nait?, Institute of the Lithuanian Language, Lithuania
+ Costanza Navarretta, University of Copenhagen, Denmark
+ Stephan Oepen, University of Oslo, Norway
+ Oscar T?ckstr?m, Google Inc.
To inquire about the submission and reviewing process or generally the
scientific programme of the conference, please email
"nodalida15@stp.lingfil.uu.se".
LOCAL ORGANIZATION
The NoDaLiDa 2015 Organizing Committee is comprised of staff from the
Institute of the Lithuanian Language, Vilnius, Lithuania:
+ Jolanta Zabarskaite
+ Violeta Meili?nait?
For all practical inquiries, please email "lki@lki.lt".
------------------------------
Message: 2
Date: Tue, 16 Dec 2014 09:27:18 +0800
From: Eng HAR <hamdiahmed919@gmail.com>
Subject: [Moses-support] about CCG factored-based model
To: moses-support@mit.edu
Message-ID:
<CADqQR4ztfjzwOA4Z9+r6QOmZtxaMrt+Z=1YrRH1Qr7g3=kTVKQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
I'm trying to train a model with CCG supertags for the target (English)
cause my model from Arabic into English .
Actually i found how to deal with POStaggs , but what about CCG supertags ?
What can i change exactly ?
Thanx alot
% train-model.perl \
--root-dir pos \
--corpus factored-corpus/proj-syndicate.1000 \
--f de --e en \
--lm 0:3:factored-corpus/surface.lm:0 \
--lm 2:3:factored-corpus/pos.lm:0 \
--translation-factors 0-0,2 \
--external-bin-dir .../tools
--
?? ???? ?????? ????? ??????? ?? ?????
*Hamdi Ahmed Rajeh*
*Hunan University - China*
*Phd Researcher*
*0086-15211108249*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20141216/2e749c0c/attachment-0001.htm
------------------------------
Message: 3
Date: Wed, 17 Dec 2014 20:54:24 -0500
From: Philipp Koehn <phi@jhu.edu>
Subject: Re: [Moses-support] about CCG factored-based model
To: Eng HAR <hamdiahmed919@gmail.com>
Cc: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID:
<CAAFADDB4Go2biv+BVChPHxvJYnqf=LeZ6FD9dixqEVNUL1HOcw@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
Hi,
the factors do not have any real meaning to the translation engines.
So if you use POS tags or CCG supertags, you can use the exact
same setup.
One comment on your training command: you use factor 0 and 2
in the output, but not factor 1. Maybe you should change this to
factor 0 and 1.
-phi
On Mon, Dec 15, 2014 at 8:27 PM, Eng HAR <hamdiahmed919@gmail.com> wrote:
> I'm trying to train a model with CCG supertags for the target (English)
> cause my model from Arabic into English .
> Actually i found how to deal with POStaggs , but what about CCG supertags ?
> What can i change exactly ?
>
> Thanx alot
>
> % train-model.perl \
> --root-dir pos \
> --corpus factored-corpus/proj-syndicate.1000 \
> --f de --e en \
> --lm 0:3:factored-corpus/surface.lm:0 \
> --lm 2:3:factored-corpus/pos.lm:0 \
> --translation-factors 0-0,2 \
> --external-bin-dir .../tools
>
>
> --
> ?? ???? ?????? ????? ??????? ?? ?????
>
> Hamdi Ahmed Rajeh
> Hunan University - China
> Phd Researcher
> 0086-15211108249
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
------------------------------
Message: 4
Date: Thu, 18 Dec 2014 08:55:41 +0000 (UTC)
From: Arefeh Kazemi <arefeh_kazemi@yahoo.com>
Subject: [Moses-support] problem with loading binarized rule -table
To: Moses-support <moses-support@mit.edu>
Message-ID:
<475669775.398843.1418892941775.JavaMail.yahoo@jws10080.mail.ne1.yahoo.com>
Content-Type: text/plain; charset="utf-8"
Hi everybody
I'm trying to tune hiero model in moses with this command:
nohup nice ~/mosesdecoderCode/scripts/training/mert-moses.pl?? ~/datasets/m-tune.en ~/datasets/m-tune.fa \
~/mosesdecoderCode/bin/moses_chart --decoder-flags="-threads all" train/model/moses.ini --no-filter-phrase-table --mertdir ~/mosesdecoderCode/bin/ --nbest=100 > mert.out
I use --no-filter-phrase-table option because I have a binary rule table which is made by this command:/home/mosesdecoderCode/bin/CreateOnDiskPt 1 1 5 20 2 train/model/rule-table.gz train/model/rule-table-binary
(the binary rule table was made without? any error and its size is 7G )
and I updated my moses.ini file with my binary rule table:PhraseDictionaryMemory name=TranslationModel0 num-features=4 path=/home/experiments/16dec/train/model/rule-table-binary input-factor=0 output-factor=0
the tuning step raise this error up:
Exception: util/file.cc:152 in std::size_t util::PartialRead(int, void*, std::size_t) threw FDException because `ret < 0'.
Is a directory in /home/akazemi/experiments/16dec/train/model/rule-table-binary while reading 6 bytes in file /home/akazemi/experiments/16dec/train/model/rule-table-binary
Exit code: 1
The decoder died. CONFIG WAS -weight-overwrite 'PhrasePenalty0= 0.057143 WordPenalty0= -0.285714 TranslationModel0= 0.057143 0.057143 0.057143 0.057143 TranslationModel1= 0.285714 LM0= 0.142857'
is there anything wrong with this commands?
Thanks a lot!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20141218/85d20ddc/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 98, Issue 45
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 98, Issue 45"
Post a Comment