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. DiscoMT at EMNLP 2017 - EXTENDED DEADLINE: June 9 (Jorg Tiedemann)
2. Chinese tokenizer / detokenizer (segmenter / unsegmenter)
(Vincent Nguyen)
3. Re: Request for help w/ "The build failed." (daideqi)
4. NPLM Installation (Sanjanashree Palanivel)
----------------------------------------------------------------------
Message: 1
Date: Mon, 29 May 2017 21:26:46 +0300
From: Jorg Tiedemann <tiedeman@gmail.com>
Subject: [Moses-support] DiscoMT at EMNLP 2017 - EXTENDED DEADLINE:
June 9
To: moses-support <moses-support@mit.edu>
Message-ID: <D455080F-8099-40BD-9DCB-E438C25CC3C2@gmail.com>
Content-Type: text/plain; charset="utf-8"
************ EXTENDED DEADLINE FOR PAPER SUBMISSIONS: June 9, 2017 **************************
Third Workshop on Discourse in Machine Translation (DiscoMT'17)
http://www.idiap.ch/workshop/DiscoMT <http://www.idiap.ch/workshop/DiscoMT>
In conjunction with EMNLP 2017, Copenhagen, Denmark
8 September 2017
Last call for papers
We invite submissions to the Third Workshop on Discourse in Machine Translation, held in conjunction with EMNLP 2017, Copenhagen. The first two DiscoMT workshops were held in 2013 at ACL in Sofia, and in 2015 at EMNLP in Lisbon. Our poster sessions, to which all presenters are invited to contribute, are held jointly with the WMT ones. In addition, shared tasks on pronoun translation or prediction were organized in 2015 and 2016, and will be held in 2017 as well.
TOPICS
DiscoMT 2017 solicits submissions on any the following topics and any language pairs, but also welcomes submissions that link discourse studies with machine translation in some other way.
- discourse processing in support of MT:
. textual coherence, including anaphora, coreference, tense, aspect and modality
. textual cohesion, including lexical consistency
. discourse structure, including use of connectives and information structuring devices
. topic structure
. consistency in style and register;
- MT techniques for obtaining document-level consistency and domain adaptability;
- MT techniques for structured documents;
- methods and algorithms to handle discourse-level phenomena in:
. neural MT
. statistical phrase-based or hierarchical MT
. example-based or rule-based MT;
- uses of MT in processing discourse-level phenomena;
- techniques for evaluating the effect of efforts targeting
discourse-level phenomena in SMT and their influence on MT quality;
- quantitative studies on the impact of discourse-level phenomena
on current MT systems vs. discourse-aware ones.
SUBMISSION INSTRUCTIONS
We solicit previously unpublished work, presented either as long or short papers, following the EMNLP 2017 formatting guidelines. Long papers should have at most 8 pages of content, not including references. Short papers are limited to 4 pages of content, not including references. There is no constraint on the size of the reference list. Submissions should be anonymous and not disclose in any way the identity of the author(s). Submissions should be made using the Softconf system and the EMNLP formatting instructions.
IMPORTANT DATES
Submission deadline: Friday, June 9, 2017
Decision notification: Friday, June 30, 2017
Final versions due: Friday, July 14, 2017
Workshop at EMNLP: Friday, Sept 8, 2017
CO-CHAIRS AND ORGANIZERS
Bonnie Webber, University of Edinburgh
Andrei Popescu-Belis, Idiap Research Institute
J?rg Tiedemann, University of Helsinki
PROGRAM COMMITTEE
Mauro Cettolo, Fondazione Bruno Kessler, Trento, Italy
Filip Ginter, University of Turku, Finland
Liane Guillou, Brainnwave, Edinburgh, UK
Christian Hardmeier, University of Uppsala, Sweden
Shafiq Joty, Qatar Computing Research Institute, Doha, Qatar
Lori Levin, Carnegie Mellon University, Pittsburgh, PA, USA
Sharid Loaiciga Sanchez, University of Geneva, Switzerland
Ekaterina Lapshinova-Koltunski, Saarland University, DE
Ngoc-Quang Luong, Nuance Communications, Belgium
Thomas Meyer, Google, Zurich, Switzerland
Preslav Nakov, Qatar Computing Research Institute, Doha, Qatar
Michal Novak, Charles University, Prague CZ
Maja Popovic, DFKI, Berlin DE
Annette Rios, University of Zurich, Switzerland
Rico Sennrich, University of Edinburgh, UK
Lucia Specia, University of Sheffield, UK
Sara Stymne, University of Uppsala, Uppsala, Sweden
Yannick Versley, University of Heidelberg, Heidelberg, Germany
Martin Volk, University of Zurich, Switzerland
Min Zhang, Soochow University, Suzhou, China
Sandrine Zufferey, University of Bern, Switzerland
SHARED TASK
The details of the 2017 shared task will be published at
http://www.idiap.ch/workshop/DiscoMT/shared-task <http://www.idiap.ch/workshop/DiscoMT/shared-task>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170529/02499df9/attachment-0001.html
------------------------------
Message: 2
Date: Mon, 29 May 2017 20:31:48 +0200
From: Vincent Nguyen <vnguyen@neuf.fr>
Subject: [Moses-support] Chinese tokenizer / detokenizer (segmenter /
unsegmenter)
To: moses-support <moses-support@mit.edu>
Message-ID: <8e219b6e-5e80-691a-e147-5d80ba0c57bd@neuf.fr>
Content-Type: text/plain; charset=utf-8; format=flowed
Hello team,
I have read many post and it looks like most people tend to use the
Stanford segmenter.
Do you have some good experience with other tools ?
Also, what "detokenizer" do you actually use. It seems, that it is not
just a question of removing space, especially when Chinese target
contains some non chinese words / symbols.
Thanks for your insight,
Vincent.
------------------------------
Message: 3
Date: Tue, 30 May 2017 11:03:07 +0000 (UTC)
From: daideqi <daideqi@yahoo.com>
Subject: Re: [Moses-support] Request for help w/ "The build failed."
To: <moses-support@mit.edu>, Hieu Hoang <hieuhoang@gmail.com>, daideqi
<daideqi@yahoo.com>, Kenneth Heafield <moses@kheafield.com>
Message-ID: <877957883.2418538.1496142187045@mail.yahoo.com>
Content-Type: text/plain; charset=UTF-8
Hi Kenneth,
Thanks! I must confess that I fought and fought over the past 3-day weekend trying to get Moses and Moses for Mere Mortals to work on my Windows 10 Ubuntu install. It was so painful and overheated my box too (a dell inspirion i7-6700 16GB RAM and running Windows 10). And nothing worked! Try as I might, something always failed at the end.
So, it's back to the drawing board for me. I'm thinking of installing Cygwin and trying Moses on that. My *nix-foo isn't the best, but I'm not a novice. Trying to get Moses to work has been surprisingly difficult, at least for me. Back to work...
Wax on...wax off...
All the Best,
Chaz
--------------------------------------------
On Mon, 5/29/17, Kenneth Heafield <moses@kheafield.com> wrote:
Subject: Re: [Moses-support] Request for help w/ "The build failed."
To: moses-support@mit.edu, "Hieu Hoang" <hieuhoang@gmail.com>, "daideqi" <daideqi@yahoo.com>
Date: Monday, May 29, 2017, 3:08 AM
A symlink
for CreateProbingPT2 has nothing to do with KenLM. The
symlink already exists and the build system is trying to
make it again (this also means not windows). I suppose we
should be using ln -sf.
Try deleting CreateProbingPT2 then rebuilding.
Kenneth
On May 29, 2017 1:04:25 AM
GMT+01:00, Hieu Hoang <hieuhoang@gmail.com>
wrote:
are you using Windows 10, or Ubuntu
14?? It seems you are using a Windows file system and this
is causing some unit tests in KenLM to fail.
I would recommend
you do everything on Linux
* Looking for MT/NLP opportunities *
Hieu Hoang
http://moses-smt.org/
On 28
May 2017 at 00:50, daideqi <daideqi@yahoo.com>
wrote:
Hi,
Respectfully request help with Moses.? I'm trying to
compile it on Windows 10 Ubuntu 14.04.5 LTS. I successfully
built Moses yesterday but decided to delete the mosesdecoder
folder and rebuild for practice.? Unfortunately, it's
not working anymore, and I'm following the instructions
that the system gave me.? As an aside, I got this error
after running the recommended bjam command:
? ? ? ? ? ? ? ? ? ? ? ? ? ln: failed to create
symbolic link ?CreateProbingPT2?: File exists
Would be grateful for assistance that can be provided.
Very Respectfully,
Chaz
______________________________
_________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/
mailman/listinfo/moses-support
------------------------------
Message: 4
Date: Tue, 30 May 2017 16:38:25 +0530
From: Sanjanashree Palanivel <sanjanashree@gmail.com>
Subject: [Moses-support] NPLM Installation
To: moses-support@mit.edu
Message-ID:
<CAAc_kp6zQX3_cPVS81w8X8=_eChgj3UPPy1M827oEgmSURJM7A@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Dear All,
How to install NPLM , the makefile is not found in src diectory
--
Thanks and regards,
Sanjanasri J.P
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170530/81612bfb/attachment.html
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 127, Issue 43
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 127, Issue 43"
Post a Comment