Moses-support Digest, Vol 126, Issue 40

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 Papers of The 13th China Workshop on Machine
Translation (CWMT 2017), September 27 ~29, 2017, Dalian, China
(Qun Liu)
2. Re: Unable to translate the in file became out file!
(Despina Mouratidi)


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

Message: 1
Date: Fri, 28 Apr 2017 17:09:23 +0100
From: Qun Liu <liuquncn@gmail.com>
Subject: [Moses-support] Call for Papers of The 13th China Workshop on
Machine Translation (CWMT 2017), September 27 ~29, 2017, Dalian, China
To: moses-support@mit.edu
Message-ID: <4fd02530-2c05-26f6-df03-e95541a69efb@gmail.com>
Content-Type: text/plain; charset="utf-8"

*** Apologies for Multiple Postings ***


Call for Papers of The 13th China Workshop on Machine Translation
(CWMT 2017)


September 27 ~29, 2017, Dalian, China

The 13th China Workshop on Machine Translation (CWMT 2017), organized by
the Chinese Information Processing Society of China, will be held at
Dalian University of Technology, China, on September 27-29, 2017. The
successive twelve workshops were successfully held by various institutes
and universities. Among these, several activities and shared tasks were
successfully organized, such as the Machine Translation Evaluation
(2007, 2008, 2009, 2011, 2013, 2015), and strategic planning meetings
(2010, 2012) as well. CWMT plays an important role in strengthening and
promoting the research and development of Machine Translation (MT) in
China, it becomes a leading academic activity in the field of Natural
Language Processing (NLP).

The CWMT aims at providing a forum to facilitate communication and
academic exchanges among domestic and foreign scholars on the latest
developments in the field of MT. CWMT 2017 features keynote speeches to
be delivered by renowned experts in the field of MT; MT evaluation
campaigns focusing on languages between Chinese and
English/Mongolian/Tibetan/Uyghur/Japanese translations; MT Panel and MT
in Practice to explore the leading edge technologies and applications in
MT; and a best paper award to be distributed during the conference. An
exhibition of commercial and research systems will be held during the
conference to bring together the users, developers and researchers of
MT. This conference will offer them a great opportunity to share and
exchange valuable experiences on MT, and thus advance MT research and
development in the region.

Papers are invited on substantial, original and unpublished research on
all aspects of MT and NLP, including, but not limited to:
? Dictionary, corpus processing and tool development for machine translation
? Machine translation models and methods, including rule-based,
example-based, statistical and neural machine translation
? Pre-processing and post-processing for machine translation
? Multi-engine translation system
? Machine translation evaluation methodologies
? Fundamental technologies for machine translation, such as word
alignment, phrase extraction, name entity recognition and translation,
lexical analysis, parsing, semantic analysis and document analysis for
machine translation
? Machine translation applications, including cross-language information
retrieval, computer-assisted translation, embedded translation,
multilingual dialogue and speech translation
? Machine translation of minority languages
? Challenges and opportunities for machine translation in Internet era

The language of the Workshop is Chinese and English. For English
manuscripts, it will be published in the proceedings with Springer in
theCommunications in Computer and Information Science
<http://www.springer.com/series/7899>series. The format of the
manuscripts should followSpringer LNCS Authors Instructions
<http://www.springer.com/cn/computer-science/lncs/conference-proceedings-guidelines>,
and the number of pages should be limited to 10-12 pages for long paper
and 6 pages for short paper. For Chinese manuscripts, it will be
published separately in a conference proceedings. Selected excellent
Chinese manuscripts will be published by the Journal of Chinese
Information Processing.

Papers will be undertaken by a double-blind review. The papers submitted
for review must not contain authors' names and affiliations.
Furthermore, self-references that reveal the author's identity, for
example, "We showed (Authors? name, 2017) ...", must be avoided.
Instead, use citations such as "Authors? name (2017) showed ...".

Submission System:https://easychair.org/conferences/?conf=cwmt2017
Conference main page:http://ee.dlut.edu.cn/CWMT2017/index.html


Important Dates

Full Paper Submission: July 15, 2017
Notification of Acceptance: August 25, 2017
Final Manuscript Submission: September 10, 2017
Registration: September 1, 2017
Conference: September 27-29, 2017


Contact

Conference Chair: Qun LIU (Institute of Computing Technology, Chinese
Academy of Sciences)
Program Co-chairs: Derek F. Wong (University of Macau), Deyi XIONG
(Soochow University)
Email: cwmt-organization@googlegroups.com


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170428/6591f5c9/attachment-0001.html

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

Message: 2
Date: Fri, 28 Apr 2017 19:39:37 +0300
From: Despina Mouratidi <dmouratidi@gmail.com>
Subject: Re: [Moses-support] Unable to translate the in file became
out file!
To: Hieu Hoang <hieuhoang@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAJJG54mf39JhmRHXZVnUxOhUqyD5t0PQb5U18y-6kXHcfkH4hQ@mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Thank you for the quik response.
Unfortunatelly it happens the same thing when I am typing

./moses -f ~/Desktop/moses/train_ken/model/moses.ini

in ~Desktop/moses/moses/bin directory. All the words that I am using are
from the phrase table.

For excample I am typing

this is
Translating: this is
Line 2: Initialize search took 0.000 seconds total
Line 2: Collecting options took 0.024 seconds at moses/Manager.cpp Line 141
Line 2: Search took 0.000 seconds
this is
BEST TRANSLATION: this|UNK|UNK|UNK is|UNK|UNK|UNK [11] [total=-208.787]
core=(-200.000,-2.000,2.000,0.000,0.000,0.000,0.000,-0.234,0.000,0.000,-0.201,0.000,0.000,0.000,-80.590)

Line 2: Decision rule took 0.000 seconds total
Line 2: Additional reporting took 0.000 seconds total
Line 2: Translation took 0.024 seconds total
reset caches


2017-04-27 14:09 GMT+03:00 Hieu Hoang <hieuhoang@gmail.com>:

> it looks like the words in your input is are not in your phrase-table. By
> default they will just be copied to the output as-is.
>
>
>
> * Looking for MT/NLP opportunities *
> Hieu Hoang
> http://moses-smt.org/
>
>
> On 27 April 2017 at 10:41, Despina Mouratidi <dmouratidi@gmail.com> wrote:
>
>> Hello guys...
>>
>> I am trying to translate with moses but when I am typing
>> ./moses -f ~/Desktop/moses/train_ken/model/moses.ini < ~/Desktop/in >
>> ~/Desktop/out in my directory the out file became the in file.
>>
>> Thus,
>> Defined parameters (per moses.ini or switch):
>> config: /home/despina/Desktop/moses/train_ken/model/moses.ini
>> distortion-limit: 6
>> feature: UnknownWordPenalty WordPenalty PhrasePenalty
>> PhraseDictionaryCompact name=TranslationModel0 num-features=4
>> path=/home/despina/Desktop/moses/train_ken/model/phrase-table
>> LexicalReordering name=LexicalReordering0 num-features=6
>> type=wbe-msd-bidirectional-fe-allff input-factor=0 output-factor=0
>> path=/home/despina/Desktop/moses/train_ken/model/reordering Distortion
>> IRSTLM name=LM0 factor=0 path=/home/despina/Desktop/moses/lm2/
>> corpus.en-fr.blm.fr order=3
>> input-factors: 0
>> mapping: 0 T 0
>> weight: LexicalReordering0= 0.0693229 0.0693229 0.0693229 0.0693229
>> 0.0693229 0.0693229 Distortion0= 0.00636699 LM0= 0.115539 WordPenalty0=
>> -0.231077 PhrasePenalty0= 0.046216 TranslationModel0= 0.046216 0.046216
>> 0.046216 0.046216 UnknownWordPenalty0= 1
>> line=UnknownWordPenalty
>> FeatureFunction: UnknownWordPenalty0 start: 0 end: 0
>> line=WordPenalty
>> FeatureFunction: WordPenalty0 start: 1 end: 1
>> line=PhrasePenalty
>> FeatureFunction: PhrasePenalty0 start: 2 end: 2
>> line=PhraseDictionaryCompact name=TranslationModel0 num-features=4
>> path=/home/despina/Desktop/moses/train_ken/model/phrase-table
>> FeatureFunction: TranslationModel0 start: 3 end: 6
>> line=LexicalReordering name=LexicalReordering0 num-features=6
>> type=wbe-msd-bidirectional-fe-allff input-factor=0 output-factor=0
>> path=/home/despina/Desktop/moses/train_ken/model/reordering
>> Initializing Lexical Reordering Feature..
>> FeatureFunction: LexicalReordering0 start: 7 end: 12
>> line=Distortion
>> FeatureFunction: Distortion0 start: 13 end: 13
>> line=IRSTLM name=LM0 factor=0 path=/home/despina/Desktop/moses/lm2/
>> corpus.en-fr.blm.fr order=3
>> FeatureFunction: LM0 start: 14 end: 14
>> Loading UnknownWordPenalty0
>> Loading WordPenalty0
>> Loading PhrasePenalty0
>> Loading LexicalReordering0
>> Loading Distortion0
>> Loading LM0
>> Language Model Type of /home/despina/Desktop/moses/lm2/
>> corpus.en-fr.blm.fr is 1
>> Language Model Type is 1
>> starting to use OOV words [<unk>]
>> OOV code is 0
>> OOV code is 0
>> LM0 LanguageModelIRST::Load() m_unknownId=0
>> Loading TranslationModel0
>> Created input-output object : [0.172] seconds
>> Translating: hello
>> Line 0: Initialize search took 0.000 seconds total
>> Line 0: Collecting options took 0.000 seconds at moses/Manager.cpp Line
>> 141
>> Line 0: Search took 0.000 seconds
>> BEST TRANSLATION: hello|UNK|UNK|UNK [1] [total=-105.310]
>> core=(-100.000,-1.000,1.000,0.000,0.000,0.000,0.000,0.000,0.
>> 000,0.000,0.000,0.000,0.000,0.000,-48.354)
>> Line 0: Decision rule took 0.000 seconds total
>> Line 0: Additional reporting took 0.000 seconds total
>> Line 0: Translation took 0.000 seconds total
>> reset caches
>> reset mmap
>> Name:moses VmPeak:565984 kB VmRSS:49036 kB RSSMax:370304 kB
>> user:0.136 sys:0.104 CPU:0.240 real:0.238
>>
>>
>> Thanks in advance
>> Despina
>>
>>
>>
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20170428/64957181/attachment.html

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

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


End of Moses-support Digest, Vol 126, Issue 40
**********************************************

Tweet