Moses-support Digest, Vol 103, Issue 1

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. 2nd Call for Participation: WAT2015 (The 2nd Workshop on
Asian Translation) (Toshiaki Nakazawa)
2. Factored Model decoder fail !! (Marwa Refaie)

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

Message: 1
Date: Fri, 01 May 2015 13:43:42 +0900
From: Toshiaki Nakazawa <nakazawa@pa.jst.jp>
Subject: [Moses-support] 2nd Call for Participation: WAT2015 (The 2nd
Workshop on Asian Translation)
To: moses-support@mit.edu
Message-ID: <m2oam4x5z5.wl-nakazawa@pa.jst.jp>
Content-Type: text/plain; charset=US-ASCII

Dear all MT researchers/users,

This is the 2nd call for participation to the 2nd Workshop on Asian
Translation (WAT2015).

UPDATES:

1. Korean->Japanese patent translation subtask is added.
http://lotus.kuee.kyoto-u.ac.jp/WAT/#task.html

2. The test data for Chinese->Japanese and Korean->Japanese patent
translation subtasks will be released on May 8th and 25th
respectively. (Those for scientific paper translation subtasks have
already been released.)
http://lotus.kuee.kyoto-u.ac.jp/WAT/patent/index.html

3. Important dates are fixed. WAT2015 participants must submit their
translation results by ***August 16, 2015***.
http://lotus.kuee.kyoto-u.ac.jp/WAT/#important-dates.html

NOTICE:

To join the evaluation campaign, you need to register to WAT2015. See
registration page and register now!
http://lotus.kuee.kyoto-u.ac.jp/WAT/registration/index.html

********************************************************************
Participants of the previous WAT2014 are also required to register
again to WAT2015
********************************************************************

Best regards,

---------------------------------------------------------------------------
WAT 2015
(The 2nd Workshop on Asian Translation)
http://lotus.kuee.kyoto-u.ac.jp/WAT/
October 16, 2015, Kyoto, Japan

Following the success of the previous Workshop on Asian Translation
(WAT2014), WAT2015 brings together machine translation researchers and
users to try, evaluate, share and discuss brand-new ideas of machine
translation. We are working toward the practical use of machine
translation among all Asian countries.

For the 2nd WAT, we adopt new translation subtasks
"Chinese-to-Japanese and Korean-to-Japanese patent translation" in
addition to the subtasks that were conducted in WAT2014.

TASK
----

The task is to improve the text translation quality for scientific
papers and patent documents. Participants choose any of the subtasks
in which they would like to participate and translate the test data
using their machine translation systems. The WAT organizers will
evaluate the results submitted using automatic evaluation and human
evaluation. We will also provide a baseline machine translation.

Subtasks:
Scientific Paper Subtask:
Japanese --> English
English --> Japanese
Japanese --> Chinese
Chinese --> Japanese
Patent Subtask: <= NEW!
Chinese --> Japanese
Korean --> Japanese

Dataset:
For the scientific paper subtask, WAT uses ASPEC (Asian Scientific
Paper Excerpt Corpus) for the dataset including training, development,
development test and test data. Participants must get a copy of ASPEC
by themselves from http://lotus.kuee.kyoto-u.ac.jp/ASPEC/

For the patent subtask, WAT uses the JPO Patent Corpus, which was
constructed by the Japan Patent Office (JPO). This corpus consists of
1 million Chinese-Japanese and Korean-Japanese parallel sentences from
patent descriptions with four categories. Participants of the patent
subtask are required to obtain the data from the WAT2015 site for the
JPO Patent Corpus.
http://lotus.kuee.kyoto-u.ac.jp/WAT/patent/index.html

Automatic evaluation:
We are providing an automatic evaluation server. It is for free for
everyone, but you need to create an account for evaluation. Just
showing the list of evaluation results does not require an account.

Registration: http://lotus.kuee.kyoto-u.ac.jp/WAT/registration/index.html
Eval. result: http://lotus.kuee.kyoto-u.ac.jp/WAT/evaluation/index.html

Human evaluation:
Human evaluation will be carried out using crowdsourcing. Participants
can submit translation results a maximum of
twice. Sentence-by-sentence pair-wise evaluation compared to the
baseline system will be carried out. The crowdsourcing workers will be
asked to judge which translation is better than the other in view of
adequacy and fluency. All systems will be ranked by the percentage of
translations judged to improve upon the baseline system.

INVITED TALK
------------

We are planning to have an invited talk as follows:

Speaker: Dr. Haizhou Li
Research Director of the Institute for Infocomm Research in Singapore
Principal Scientist and Department Head of Human Language Technology
Title: Adequacy-Fluency Metrics: Evaluating MT in the Continuous Space Model Framework

Please visit the homepage of WAT for the biography of the speaker.
http://lotus.kuee.kyoto-u.ac.jp/WAT/#invited-talk.html

REGISTRATION
------------

The registration for task participants:
The registration fee is FREE for all participants.
http://lotus.kuee.kyoto-u.ac.jp/WAT/registration/index.html

The registration for WAT2015 audiences:
There is no need to register in advance. The registration fee is FREE
for all audiences include participants.

IMPORTANT DATES
---------------

Submission due for crowdsourcing evaluation August 16, 2015
System description draft paper due September 20, 2015
Review feedback September 27, 2015
System description camera-ready paper due October 4, 2015
WAT 2015 October 16, 2015

PAPER
-----

Participants who submit results for human evaluation should submit
description papers of their translation systems and evaluation
results.

We strongly prefer that papers include a section entitled "Issues for
Context-aware Machine Translation" which discusses the importance and
usefulness of context.

ORGANIZERS
----------

Toshiaki Nakazawa (Japan Science and Technology Agency (JST))
Hideya Mino (National Institute of Information and Communications Technology (NICT))
Isao Goto (Japan Broadcasting Corporation (NHK))
Graham Neubig (Nara Institute of Science and Technology (NAIST))
Eiichiro Sumita (National Institute of Information and Communications Technology (NICT))
Sadao Kurohashi (Kyoto University)

CONTACT
-------

wat@nlp.ist.i.kyoto-u.ac.jp

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

--
Toshiaki Nakazawa (Researcher)
Japan Science and Technology Agency (JST)
(@ Graduate School of Informatics, Kyoto University)
Yoshida-honmachi, Sakyo-ku, Kyoto, 606-8501, Japan
tel: +81-75-753-5346, fax: +81-75-753-5962
nakazawa@pa.jst.jp / nakazawa@nlp.ist.i.kyoto-u.ac.jp

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

Message: 2
Date: Fri, 1 May 2015 09:33:28 +0000
From: Marwa Refaie <basmallah@hotmail.com>
Subject: [Moses-support] Factored Model decoder fail !!
To: "moses-support@mit.edu" <moses-support@mit.edu>
Message-ID: <DUB118-W21BADD5D9182EC806D30ABBAD50@phx.gbl>
Content-Type: text/plain; charset="windows-1256"

I try to build a factored model with word|pos. After fixing all erroros, I got the "segmentation fault" error, so I compress the phrase table by
~/mosesdecoder/bin/CreateOnDiskPt 2 2 4 100 2 ~/April/small/-dir/model/phrase-table.0-0,1.gz phrase-table.folder
Now I have this error !!! I change the ini file but still stuck here ... Please any help ??
On-disk phrase table has 2 source factors.. The ini file specified 1 source factors .... Aborted (core dumped)or Segmentation Fault (core dumped)orNo phrase dictionary with index 1 available!
as I change ini Input factor or mapping steps. English / Arabic corpus
Its|VBD complement|NN the|NN error|NN rate,|NN is|NN the|NN proportion|NN of|NN incorrect|NN predictions|NN on|NN the|NN same|NN data.|NN See|VBD Also:|NN hold|NN out|NN sample,|NN Machine|DTNN Learning.|DTJJ
???????|NN ?????|NN ????????|DTNN ????????|VBD ???|NN ????|NN ?????|JJ ??????|VBP ?????|NN ?????|VBP ???|IN ????????|DTNN .|PUNC ????|VB ????|NN :|PUNC ?????|NN ?????|VBP ???|IN ????????.|DTNN
Phrase Table 0-0,1] proposed the ||| ]|NN ?????|VBD ||| 1 0.102035 1 0.124013 ||| 0-0 1-1 2-1 ||| 1 1 1 ||| |||] suggests analysis of ||| ]|NN ????|VBP ?????|NN ||| 1 0.00298151 1 0.00967381 ||| 0-0 1-1 2-2 3-2 ||| 1 1 1 ||| |||
Moses.ini# input factors[input-factors]01
# mapping steps[mapping]0 T 0
[distortion-limit]6
# feature functions[feature]UnknownWordPenaltyWordPenaltyPhrasePenalty#PhraseDictionaryMemory name=TranslationModel0 num-features=4 path=/home/marwa/Phd/April/bilmpos/small/-dir/model/phrase-table.0-0,1.gz input-factor=0 output-factor=0,1
PhraseDictionaryOnDisk name=TranslationModel0 num-features=4 path=/home/marwa/Phd/April/bilmpos/small/-dir/model/phrase-table.folder input-factor=0 output-factor=0,1
DistortionKENLM name=LM0 factor=2 path=/home/marwa/Phd/April/bilmpos/small/pos.binary order=5KENLM name=LM1 factor=0 path=/home/marwa/Phd/April/bilmpos/small/surface.binary order=5

Marwa N. Refaie

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150501/be476e22/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 103, Issue 1
*********************************************

Moses-support Digest, Vol 103, Issue 1

0 Response to "Moses-support Digest, Vol 103, Issue 1"