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. LM Interpolation (Fathima Farhath Farook)
2. Call for Papers: Workshop on Language Technologies and Human
Translators at MT Summit XVI (Atsushi FUJITA)
3. A new problem when tuning in Errors when training: No
extract.o.sorted.gz (???)
----------------------------------------------------------------------
Message: 1
Date: Wed, 7 Jun 2017 12:44:10 +0530
From: Fathima Farhath Farook <fathimafarhath@gmail.com>
Subject: [Moses-support] LM Interpolation
To: moses-support@mit.edu
Message-ID:
<CAP6fBzAk6biRrHPK0o7b6UqD0kNhY1S774x0_Va70nfMQMWcwA@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
Dear All,
Currently I am trying to interpolate LMs in EMS with SRILM. The data is not
much larger ( few thousand lines). the test being started 2 days before.
But it didn't end up yet( neither crashed) the state is still being shown
as running. But as per the log files, the system state is at "computing
lambdas..." without moving forward for many days. I tried it many times,
same happens.
can anyone please instruct me in this regard.
thanks in advance
--
Regards,
Farhath Farook
<http://farhathforever.blogspot.com/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170607/5cbe8f9c/attachment-0001.html
------------------------------
Message: 2
Date: Wed, 07 Jun 2017 16:30:56 +0900 (JST)
From: Atsushi FUJITA <fujita@paraphrasing.org>
Subject: [Moses-support] Call for Papers: Workshop on Language
Technologies and Human Translators at MT Summit XVI
To: moses-support@mit.edu
Message-ID:
<20170607.163056.1223755143841819003.fujita@paraphrasing.org>
Content-Type: Text/Plain; charset=us-ascii
*** Apologies for Multiple Postings ***
Call for Papers
Workshop on Language Technologies and Human Translation (LTHT2017)
The aim of the workshop on "Language Technologies and Human
Translation" is to bring together NLP researchers, industry users of
MT technologies, practitioners in LSPs, translation researchers, and
translators to discuss issues related to language technologies and its
real and potential impact on human translation and translation
industries.
We invite original papers on the following topics, but also welcome
other related ideas.
* requirement for MT technologies: from the point of view of use by
LSPs, individual translators and lay people, e.g., what is the
determining factors for people to use or not use MT?
* evaluation of MT:, from the point of view of usability of
translation services in the social sphere, i.e., what is "good" MT
for social use?
* the relationship between human translators and MT:, e.g., how can MT
systems better complement the skills of human translators, how does
the use of MT change human translation activities, and how do
changes in human language activities promote the better use of MT
and related technologies?
* range of language technologies in the human translation process:,
not limited to MT and multilingual processing, e.g., how can
language technologies support authoring and pre-editing to maximize
the effect of human or machine translation?
* human factors:, i.e., what is the required competence for human
"translators" to fully take advantage of language technologies, is
it essentially the same as traditional translators' competence?
The workshop submissions are open to wide range of researchers and
practitioners with different backgrounds and approaches, for instance,
NLP researchers, MT developers, translation researchers, translators,
LSP managers, etc. We emphasize to bring together researchers and
practitioners with different backgrounds at this workshop.
Format for the paper is the same as for regular submissions for MT
Summit XVI. Long papers must be up to 12 pages for content plus
unlimited pages for references. We also solicit short papers for
smaller and more focused contributions, with up to 6 pages for content
plus unlimited pages for references. Style files (LaTeX / MS Word)
and PDF are available at MT Summit XVI website.
http://aamt.info/app-def/S-102/mtsummit/2017/call-for-contributions/call-for-papers-for-research-track/
Papers must be submitted by 23:59 PDF (GMT-0700), July 3, 2017, using
the Softconf START conference management system.
http://www.softconf.com/mtsummit-xvi/LTHT2017/
Important dates
July 3, 2017: Paper submission deadline
July 31, 2017: Notification of acceptance
August 14, 2017: Camera-ready PDF due
September 18, 2017: Workshop
If you have any questions, please feel free to contact us.
Contact: ltht2017@googlegroups.com
Website: https://ltht2017.github.io/
Organizers
Atsushi Fujita, NICT, Japan
Masaru Yamada, Kansai University, Japan
Bogdan Babych, University of Leeds, UK
Michael Carl, CBS, Denmark / Renmin University of China, China
Kyo Kageura, University of Tokyo, Japan
------------------------------
Message: 3
Date: Wed, 7 Jun 2017 21:26:38 +0800 (CST)
From: ??? <yufeifan7@126.com>
Subject: [Moses-support] A new problem when tuning in Errors when
training: No extract.o.sorted.gz
To: moses-support@mit.edu
Message-ID: <3d4c9443.be3b.15c82bc4f90.Coremail.yufeifan7@126.com>
Content-Type: text/plain; charset="gbk"
Dear all:
I tried running from the first step and successfully completed training. But when tuning, an error comes out immediately:
The command is:
mert-moses.pl /home/yuff/mosesdecoder/projectdata/accessor_variety/dev-split-trainingmodel.clean.right /home/yuff/mosesdecoder/projectdata/accessor_variety/dev-split-trainingmodel.clean.left /home/yuff/mosesdecoder/bin/moses \
train/model/moses.ini --mertdir /home/yuff/mosesdecoder/bin/ --mertargs="--sctype TER" --decoder-flag="-threads-8"
Thanks for paying attention and trying to give suggestions.
Dear all:
I am a new hand at moses and machine translation. I was trying to completing a task of translation between two unknown languages.I had completed the word segmentation and clean the corpus with the command: clean-corpus-n.perl train-split.txt right left train-split.clean 1 120
(PS:the two pararrel corpus with extension left and right)
Then I ran the train-model perl as follows:
train-model.perl -root-dir train --cores 8 --corpus /home/yuff/mosesdecoder/projectdata/accessor_variety/train-split.clean --f right --e left --alignment grow-diag-final-and --first-step 2 --reordering msd-bidirectional-fe --lm 0:3:/home/yuff/mosesdecoder/projectdata/accessor_variety/train-split.blm.left --mgiza -mgiza-cpus 2 --parallel --external-bin-dir /home/yuff/mosesdecoder/word_align_tools/
There were a lot of warnings beginning with "Use of Uninitialized Value in " coming out, without ending the executing of perl. However, after about 20 minutes, I got the error as follows:
"Executing: /home/yuff/mosesdecoder/scripts/../bin/lexical-reordering-score /home/yuff/mosesdecoder/projectdata/accessor_variety/translating_working/train/model/extract.o.sorted.gz 0.5 /home/yuff/mosesdecoder/projectdata/accessor_variety/translating_working/train/model/reordering-table. --model "wbe msd wbe-msd-bidirectional-fe"
Lexical Reordering Scorer
scores lexical reordering models of several types (hierarchical, phrase-based and word-based-extraction
terminate called after throwing an instance of 'util::ErrnoException'
what(): util/file.cc:76 in int util::OpenReadOrThrow(const char*) threw ErrnoException because `-1 == (ret = open(name, 00))'.
No such file or directory while opening /home/yuff/mosesdecoder/projectdata/accessor_variety/translating_working/train/model/extract.o.sorted.gz
Aborted (core dumped)
Exit code: 134
ERROR: Lexical reordering scoring failed at /home/yuff/mosesdecoder/scripts/training/train-model.perl line 1924."
The files under the directory "/train" are extremely small or even empty. I searched for the problem and found some others asking about that in 2012: He got the reply like this
However, '[',']' are both characters in these two languages, and uppercase and downcase letters are recognized as different ones. I'm not sure if the first step of training would downcase the letters, so I started with the second step.
I will appreciate it so much if some ones can give some suggestions. Thanks!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170607/9512a02a/attachment.html
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 45643 bytes
Desc: not available
Url : http://mailman.mit.edu/mailman/private/moses-support/attachments/20170607/9512a02a/attachment.png
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 128, Issue 10
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 128, Issue 10"
Post a Comment