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. Re: Adding a language model built on Google Web (Philipp Koehn)
2. Call for Participation: SSST-9 @ NAACL HLT 2015, 9th Workshop
on Syntax, Semantics and Structure in Statistical Translation
(Nora Aranberri)
3. Re: lattice MBR - what happened to my nbest features?
(Jeremy Gwinnup)
4. Re: lattice MBR - what happened to my nbest features?
(Barry Haddow)
----------------------------------------------------------------------
Message: 1
Date: Thu, 7 May 2015 13:57:24 -0400
From: Philipp Koehn <phi@jhu.edu>
Subject: Re: [Moses-support] Adding a language model built on Google
Web
To: Hieu Hoang <hieuhoang@gmail.com>
Cc: moses-support <moses-support@mit.edu>, Alla Rozovskaya
<sigaliyah@gmail.com>
Message-ID:
<CAAFADDD-a-K=cGgtyXFHEg9Dk_E8HfJR33KxCN7SecxoDVrV4A@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
Hi,
> what's the exact command you're using to create the translation model and
> reordering model?
>
> $mosesDir/scripts/training/train-model.perl -root-dir $outputDir/mosesFiles/
> -corpus $corpusDir/$trainFile.clean -f $source -e $target -alignment
> grow-diag-final-and -reordering msd-bidirectional-fe -lm 0:$order:$lm1
> -external-bin-dir /scratch/rozovska/mosesdecoder/tools/ -cores 2
> --max-phrase-length 7
Remove the switch "-reordering msd-bidirectional-fe" and no lexicalized
reordering model will be built.
-phi
------------------------------
Message: 2
Date: Thu, 07 May 2015 20:00:27 +0200
From: Nora Aranberri <nora.aranberri@ehu.eus>
Subject: [Moses-support] Call for Participation: SSST-9 @ NAACL HLT
2015, 9th Workshop on Syntax, Semantics and Structure in Statistical
Translation
To: moses-support@mit.edu
Message-ID: <554BA83B.5040105@ehu.eus>
Content-Type: text/plain; charset="windows-1252"
Apologies for cross-posting
--------------------------------------------
Call for participation
Ninth Workshop on Syntax, Semantics and Structure in Statistical
Translation (SSST-9)
NAACL HLT 2015 / SIGMT / SIGLEX Workshop
4 Jun 2015, Denver, Colorado
Invited speaker: Philipp Koehn
Workshop website: http://www.cs.ust.hk/~dekai/ssst/
Registration: http://naacl.org/naacl-hlt-2015/registration.html (Early
registration deadline: May 10, 2015)
----------------------------------------------------------------------
The Ninth Workshop on Syntax, Semantics and Structure in Statistical
Translation (SSST-9) seeks to bring together a large number of
researchers working on diverse aspects of structure, semantics and
representation in relation to statistical machine translation. Since its
first edition in 2006, its program each year has comprised high-quality
papers discussing current work spanning topics including: new
grammatical models of translation; new learning methods for syntax- and
semantics-based models; formal properties of synchronous/transduction
grammars (hereafter S/TGs); discriminative training of models
incorporating linguistic features; using S/TGs for semantics and
generation; and syntax- and semantics-based evaluation of machine
translation.
*** QTLeap Best Paper Award (?500,00) *** to the advance of MT using
lexical semantics and deep language processing
Program
SSST-9 - Conference Program
08:55?09:00 Opening Remarks
09:00?10:30 Session 1
09:00?10:00 Invited Talk
Philipp Koehn
10:00?10:30 Harmonizing word alignments and syntactic structures for
extracting phrasal translation equivalents
Dun Deng, Nianwen Xue and Shiman Guo
10:30?11:00 Coffee Break
11:00?12:30 Session 2
11:00?11:30 Non-projective Dependency-based Pre-Reordering with
Recurrent Neural Network for Machine Translation
Antonio Valerio Miceli Barone and Giuseppe Attardi
11:30?12:00 Translating Negation: Induction, Search And Model Errors
Federico Fancellu and Bonnie Webber
12:00?12:30 SMT error analysis and mapping to syntactic, semantic and
structural fixes
Nora Aranberri
12:30?13:55 Lunch Break
13:55?14:30 Session 3
13:55?14:00 QTLeap Best Paper Award
14:00?14:30 Unsupervised False Friend Disambiguation Using Contextual
Word Clusters and Parallel Word Alignments
Maryam Aminian, Mahmoud Ghoneim and Mona Diab
14:30?15:30 Session 4: Posters
14:30?14:35 METEOR-WSD: Improved Sense Matching in MT Evaluation
Marianna Apidianaki and Benjamin Marie
14:35?14:40 Analyzing English-Spanish Named-Entity enhanced Machine
Translation
Mikel Artetxe, Eneko Agirre, I?aki Alegria and Gorka Labaka
14:40?14:45 Predicting Prepositions for SMT
Marion Weller, Alexander Fraser and Sabine Schulte im Walde
14:45?14:50 Translation reranking using source phrase dependency features
Antonio Valerio Miceli Barone
14:50?14:55 Semantics-based pretranslation for SMT using fuzzy matches
Tom Vanallemeersch and Vincent Vandeghinste
15:30?16:00 Coffee Break
16:00?17:00 Session 5
16:00?16:30 What Matters Most in Morphologically Segmented SMT Models?
Mohammad Salameh, Colin Cherry and Grzegorz Kondrak
16:30?17:00 Improving Chinese-English PropBank Alignment
Shumin Wu and Martha Palmer
Organizers
Dekai WU, Hong Kong University of Science and Technology (HKUST)
Marine CARPUAT, University of Maryland
Eneko AGIRRE, University of the Basque Country
Nora ARANBERRI, University of the Basque Country
Program Committee
Timothy Baldwin, University of Melbourne
Ondrej Bojar, Charles University in Prague
Aljoscha Burchardt, German Research Centre for Artificial Intelligence
(DFKI)
Francisco Casacuberta, Universitat Polit?cnica de Val?ncia
Colin Cherry, National Research Council (NRC) Canada
David Chiang, USC/ISI
Stephen Clark, University of Cambridge
Kevin Duh, Nara Institute of Science and Technology (NAIST)
Marc Dymetman, Xerox Research Centre Europe
Daniel Gildea, University of Rochester
Nal Kalchbrenner, University of Oxford
Philipp Koehn, University of Edinburgh
Gorka Labaka, University of the Basque Country (UPV/EHU)
Alon Lavie, Carnegie Mellon University
Chi-kiu Lo, Hong Kong University of Science and Technology (HKUST)
Markus Saers, Hong Kong University of Science and Technology (HKUST)
Khalil Sima?an, University of Amsterdam
Ivan Vulic , University of Leuven
Taro Watanabe, Google
Andy Way, Dublin City University
Deyi Xiong, Soochow University
Fran?ois Yvon, LIMSI
Contact
Please send inquiries to ssst@cs.ust.hk.
Sponsor
This workshop is partially funded by the European Union QTLeap project
(FP7-ICT-2013-10-610516).
European Commission (http://ec.europa.eu)
QTLeap (http://qtleap.eu)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150507/3ec18a40/attachment-0001.htm
------------------------------
Message: 3
Date: Thu, 7 May 2015 14:14:18 -0400
From: Jeremy Gwinnup <jeremy@gwinnup.org>
Subject: Re: [Moses-support] lattice MBR - what happened to my nbest
features?
To: Barry Haddow <bhaddow@inf.ed.ac.uk>
Cc: moses-support@mit.edu
Message-ID: <95E4F013-FED3-4B53-A4CE-0BDDCF32EA5C@gwinnup.org>
Content-Type: text/plain; charset=utf-8
How hard would it be to append the LMBR scores to the list of features instead of overwriting it? Maybe I can tackle this at MTMA15 next week. I?m not too worried about the long runtime at least initially.
> On May 6, 2015, at 5:01 PM, Barry Haddow <bhaddow@inf.ed.ac.uk> wrote:
>
> Hi Jeremy
>
> It's been a long time since I looked at this, but I think these are the component scores in the linearised corpus bleu used in Lattice MBR (see Tromble et al (2008), section 5). They are used to rescore the nbest list, and must be implemented by replacing the original feature vectors.
>
> So it looks like lattice MBR doesn't work with nbest lists, or at least doesn't give you what you need for tuning. Do you really want to tune with lattice MBR? It's going to be very slow,
>
> cheers - Barry
>
> On 06/05/15 20:49, Jeremy Gwinnup wrote:
>> Hi,
>>
>> I?ve been attempting to experiment with lattice MBR with various settings and I see something weird happen to my nbest lists:
>>
>> 0 ||| the prime ministers of india and japan meet in tokyo ||| Distortion0= ? etc etc becomes
>>
>> 0 ||| the prime ministers of india and japan meet in tokyo ||| map: 0 w: 12 11.19 8.06 6.63 5.39
>>
>> My feature weights get replaced by map and w feature with 5 weights
>>
>> I?m setting the following as moses.ini parameters:
>> lminimum-bayes-risk
>> lmbr-p
>> lmbr-r
>> mbr-scale
>> lmbr-pruning-factor
>>
>> Anything extra that I need to know as far as what map and w are, or how to get my normal features back in the nbest list?
>>
>> Thanks!
>> -Jeremy
>> _______________________________________________
>> Moses-support mailing list
>> Moses-support@mit.edu
>> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
> --
> The University of Edinburgh is a charitable body, registered in
> Scotland, with registration number SC005336.
>
------------------------------
Message: 4
Date: Thu, 07 May 2015 20:28:47 +0100
From: Barry Haddow <bhaddow@staffmail.ed.ac.uk>
Subject: Re: [Moses-support] lattice MBR - what happened to my nbest
features?
To: Jeremy Gwinnup <jeremy@gwinnup.org>, Barry Haddow
<bhaddow@inf.ed.ac.uk>
Cc: moses-support@mit.edu
Message-ID: <2C7FE27E-8139-458E-870B-A4FBBFE6E44C@staffmail.ed.ac.uk>
Content-Type: text/plain; charset="utf-8"
Hi Jeremy
It probably won't be hard - but I haven't looked at the code in a long time.
Note that we didn't see any gain from lmbr. We only ever implemented it as reranking - not lattice rescoring - but according to the original paper that should still help
Cheers - Barry
On 7 May 2015 19:14:18 BST, Jeremy Gwinnup <jeremy@gwinnup.org> wrote:
>How hard would it be to append the LMBR scores to the list of features
>instead of overwriting it? Maybe I can tackle this at MTMA15 next week.
>I?m not too worried about the long runtime at least initially.
>
>> On May 6, 2015, at 5:01 PM, Barry Haddow <bhaddow@inf.ed.ac.uk>
>wrote:
>>
>> Hi Jeremy
>>
>> It's been a long time since I looked at this, but I think these are
>the component scores in the linearised corpus bleu used in Lattice MBR
>(see Tromble et al (2008), section 5). They are used to rescore the
>nbest list, and must be implemented by replacing the original feature
>vectors.
>>
>> So it looks like lattice MBR doesn't work with nbest lists, or at
>least doesn't give you what you need for tuning. Do you really want to
>tune with lattice MBR? It's going to be very slow,
>>
>> cheers - Barry
>>
>> On 06/05/15 20:49, Jeremy Gwinnup wrote:
>>> Hi,
>>>
>>> I?ve been attempting to experiment with lattice MBR with various
>settings and I see something weird happen to my nbest lists:
>>>
>>> 0 ||| the prime ministers of india and japan meet in tokyo |||
>Distortion0= ? etc etc becomes
>>>
>>> 0 ||| the prime ministers of india and japan meet in tokyo ||| map:
>0 w: 12 11.19 8.06 6.63 5.39
>>>
>>> My feature weights get replaced by map and w feature with 5 weights
>>>
>>> I?m setting the following as moses.ini parameters:
>>> lminimum-bayes-risk
>>> lmbr-p
>>> lmbr-r
>>> mbr-scale
>>> lmbr-pruning-factor
>>>
>>> Anything extra that I need to know as far as what map and w are, or
>how to get my normal features back in the nbest list?
>>>
>>> Thanks!
>>> -Jeremy
>>> _______________________________________________
>>> Moses-support mailing list
>>> Moses-support@mit.edu
>>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>
>>
>> --
>> The University of Edinburgh is a charitable body, registered in
>> Scotland, with registration number SC005336.
>>
--
Sent from my Android device with K-9 Mail. Please excuse my brevity.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150507/6b28d601/attachment.htm
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: not available
Url: http://mailman.mit.edu/mailman/private/moses-support/attachments/20150507/6b28d601/attachment.bat
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 103, Issue 28
**********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 103, Issue 28"
Post a Comment