Moses-support Digest, Vol 86, Issue 39

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 CfP: EACL 2014 Workshop on Hybrid Approaches to
Translation (3rd HyTra) (Reinhard Rapp)
2. Re: Regarding Bleu Score (rohit dholakia)


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

Message: 1
Date: Thu, 12 Dec 2013 20:28:00 +0100
From: "Reinhard Rapp" <reinhardrapp@gmx.de>
Subject: [Moses-support] 2nd CfP: EACL 2014 Workshop on Hybrid
Approaches to Translation (3rd HyTra)
To: <IRList@lists.shef.ac.uk>
Cc: news@multilingual.com, nodali@helsinki.fi,
lpcall@watarts.uwaterloo.ca, lr_egroup@mail.iiit.ac.in,
listmaster@loria.fr, ln@cines.fr, moses-support@mit.edu
Message-ID: <2C7CD65A618846AA874D7EBEE8259000@ASUSPC>
Content-Type: text/plain; charset="windows-1252"

Apologies for multiple postings
Please distribute to colleagues

=================================================================

2nd Call for Papers

THIRD WORKSHOP ON HYBRID APPROACHES TO TRANSLATION (HyTra 2014)

Co-located with EACL 2014 http://eacl2014.org/

Gothenburg, Sweden

April 27, 2014

Deadline for paper submissions: January 23, 2014

http://parles.upf.edu/llocs/plambert/hytra/hytra2014/

INVITED SPEAKERS

Hans Uszkoreit (Saarland University and DFKI, Germany)
Joakim Nivre (Uppsala University, Sweden)

=================================================================


WORKSHOP DESCRIPTION

The aim of the HyTra workshop series is to bring together researchers developing and applying statistical, example-based, or rule-based translation systems, and those enhancing MT systems by combining elements from different approaches, to promote discussion and sharing of ideas among them. Hereby one relevant focus is on effectively combining linguistic and data driven approaches (rule-based and statistical MT). Another focus is on hybridization in the context of human translation.

The 3rd Workshop on Hybrid Approaches to Translation (HyTra-3) intends to continue developing and empowering the research agenda in the area of Hybrid Translation already started at its first and second editions. The previous two editions (see http://www-lium.univ-lemans.fr/esirmt-hytra/ and http://hytra.barcelonamedia.org/hytra2013/) were co-located with EACL 2012 in Avignon and with ACL 2013 in Sofia, and the proceedings were published on the ACL Anthology.


TOPICS

We solicit contributions including but not limited to the following topics:

- ways and techniques of hybridization
- architectures for the rapid development of hybrid MT systems
- applications of hybrid systems
- hybrid systems dealing with under-resourced languages
- hybrid systems dealing with morphologically rich languages
- using linguistic information (morphology, syntax, semantics) to enhance statistical MT
(e.g. with hierarchical or factored models)
- using contextual information to enhance statistical MT
- bootstrapping rule-based systems from corpora
- hybrid methods in spoken language translation
- extraction of dictionaries and other large-scale resources for MT from parallel and comparable corpora
- induction of morphological, grammatical, and translation rules from corpora
- machine learning techniques for hybrid MT
- describing structural mappings between languages (e.g. tree-structures using
synchronous/transduction grammars)
- heuristics for limiting the search space in hybrid MT
- alternative methods for the fair evaluation of the output of different types of MT systems
(e.g. relying on linguistic criteria)
- system combination approaches such as multi-engine MT (parallel) or automatic post-editing (sequential)
- open source tools and free language resources for hybrid MT


SUBMISSIONS

Contributions can be short or long papers. Short paper submissions must describe original and unpublished work without exceeding five pages of content plus one extra page for references. Characteristics of short papers include: a small, focused contribution; work in progress; a negative result; an opinion piece; an interesting application nugget. Long paper submissions must describe substantial, original, completed and unpublished work without exceeding eight pages of content plus two extra pages for references. Submissions will be judged according to the criteria of the main conference (EACL 2014).

Authors are invited to submit papers on original and previously unpublished work. Formatting should be according to EACL 2014 specifications using LaTeX or MS-Word style files, see section "submission format" at http://eacl2014.org/call-for-papers. Reviewing of papers will be double-blind, so the submissions should not reveal the authors' identity.

Submission is electronic in PDF format using the START submission system at the following URL: https://www.softconf.com/eacl2014/HyTra/

Double submission policy: Parallel submission to other meetings or publications is possible but must be immediately notified to the workshop contact person (see below). If accepted, withdrawals are only possible within two days after notification.

For an accepted paper to appear in the proceedings, at least one author must register for the workshop and actually present the paper. The papers will be published in the workshop proceedings which will be made available via the ACL Anthology.


BEST PAPERS

Authors of selected papers will be invited to contribute extended versions of their papers as book chapters for an edited volume on hybrid MT.


IMPORTANT DATES

January 23, 2014: Deadline for paper submission
February 20, 2014: Notification of acceptance
March 3, 2014: Camera ready papers due
April 27, 2014: Workshop in Gothenburg


ORGANIZERS

Rafael E. Banchs (Institute for Infocomm Research, Singapore)
Marta R. Costa-jussa (Institute for Infocomm Research, Singapore)
Reinhard Rapp (Universities of Aix-Marseille and Mainz)
Patrik Lambert (Pompeu Fabra University, Barcelona)
Kurt Eberle (Lingenio GmbH, Heidelberg)
Bogdan Babych (University of Leeds)


CONTACT PERSON

Rafael E. Banchs: rembanchs (at) i2r (dot) a-star (dot) edu (dot) sg


PROGRAMME COMMITTEE

* Ahmet Aker, University of Sheffield, UK
* Bogdan Babych, University of Leeds, UK
* Rafael E. Banchs, Institute for Infocomm Research, Singapore
* Alexey Baytin, Yandex, Moscow, Russia
* N?ria Bel, Universitat Pompeu Fabra, Barcelona, Spain
* Pierrette Bouillon, ISSCO/TIM/ETI, University of Geneva, Switzerland
* Michael Carl, Copenhagen Business School, Denmark
* Marta R. Costa-jussa, Institute for Infocomm Research, Singapore
* Oliver Culo, University of Mainz, Germany
* Kurt Eberle, Lingenio GmbH, Heidelberg, Germany
* Andreas Eisele, DGT (European Commission), Luxembourg
* Marcello Federico, Fondazione Bruno Kessler, Trento, Italy
* Christian Federmann, Language Technology Lab, DFKI, Saarbr?cken, Germany
* Jos? A. R. Fonollosa, Universitat Polit?cnica de Catalunya, Barcelona, Spain
* Maxim Khalilov, TAUS, Amsterdam, The Netherlands
* Patrik Lambert, Pompeu Fabra University, Barcelona, Spain
* Udo Kruschwitz, University of Essex, UK
* Yanjun Ma, Baidu Inc., Beijing, China
* Jos? B. Mari?o, Universitat Polit?cnica de Catalunya, Barcelona, Spain
* Bart Mellebeek, University of Amsterdam, The Netherlands
* Reinhard Rapp, Universities of Aix-Marseille, France, and Mainz, Germany
* Anders S?gaard, University of Copenhagen, Denmark
* Nasredine Semmar, CEA LIST, Fontenay-aux-Roses, France
* Wade Shen, Massachusetts Institute of Technology, Cambridge, USA
* Serge Sharoff, University of Leeds, UK
* George Tambouratzis, Institute for Language and Speech Processing, Athens, Greece
* J?rg Tiedemann, University of Uppsala, Sweden
* Dekai Wu, The Hong Kong University of Science and Technology, Hong Kong, China

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20131212/6fbdf62b/attachment-0001.htm

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

Message: 2
Date: Thu, 12 Dec 2013 15:29:30 -0800
From: rohit dholakia <rdholaki@sfu.ca>
Subject: Re: [Moses-support] Regarding Bleu Score
To: Prasanth K <prasanthk.ms09@gmail.com>
Cc: moses-support <moses-support@mit.edu>, Pranjal Das
<pranjal4456@gmail.com>
Message-ID:
<CAA==LgunGtzW-PTxw-vXhXGNgkiPBd0HCz9kyZv5nJcZKqBB1A@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

I am not sure if you have looked at that Matt Post et al paper about
collecting Indian language data via crowdsourcing.

I believe the details and the corpora can be found here :

http://joshua-decoder.org/data/indian-parallel-corpora/






On Thu, Dec 12, 2013 at 7:35 AM, Prasanth K <prasanthk.ms09@gmail.com>wrote:

> Pranjal,
>
> Well, the co-relation between corpus size and BLEU score is complicated to
> attribute them to the corpus size alone, but in this case, yes. That is the
> reason why you get low scores.
>
> - Prasanth
>
>
> On Thu, Dec 12, 2013 at 4:31 PM, Pranjal Das <pranjal4456@gmail.com>wrote:
>
>> Thank you Prasanth....but why i am getting such a low bleu
>> score...actually i have a very small corpus..about 2500 sentences..is it
>> because of that ???
>>
>> *Pranjal Das*
>> Department of Information Technology,
>> Institute of Science and Technology,
>> Gauhati University,Guwahati,Assam
>> Phone- +91-8399879454
>>
>>
>> On Thu, Dec 12, 2013 at 8:58 PM, Prasanth K <prasanthk.ms09@gmail.com>wrote:
>>
>>> Hi Pranjal,
>>>
>>> Its not uncommon to observe such differences when changing the direction
>>> of translation. Translation from English to Bengali is relatively harder as
>>> Bengali is morphologically rich, making it difficult for the correct
>>> surface forms to be generated. Given that BLEU is a pattern matching
>>> algorithm comparing surface forms, the drop in the score could be partly
>>> attributed to not being able to generate the correct surface forms.
>>>
>>> You can look at the EuroMatrix, where similar patterns can be observed.
>>> Translation from English->Finnish gives better results than the other way
>>> around.
>>> http://www.statmt.org/matrix/
>>>
>>> Prasanth
>>>
>>> On Thu, Dec 12, 2013 at 4:21 PM, Pranjal Das <pranjal4456@gmail.com>wrote:
>>>
>>>> Hi all..
>>>> While doing Bengali to English translation i got a bleu score of 7.02
>>>> and doing English to Bengali i got 4.7
>>>>
>>>> why is the difference so high as i am using the same parallel corpus ??
>>>>
>>>>
>>>> *Pranjal Das*
>>>> Department of Information Technology,
>>>> Institute of Science and Technology,
>>>> Gauhati University,Guwahati,Assam
>>>> Phone- +91-8399879454
>>>>
>>>> _______________________________________________
>>>> Moses-support mailing list
>>>> Moses-support@mit.edu
>>>> http://mailman.mit.edu/mailman/listinfo/moses-support
>>>>
>>>>
>>>
>>>
>>> --
>>> "Theories have four stages of acceptance. i) this is worthless nonsense;
>>> ii) this is an interesting, but perverse, point of view, iii) this is true,
>>> but quite unimportant; iv) I always said so."
>>>
>>> --- J.B.S. Haldane
>>>
>>
>>
>
>
> --
> "Theories have four stages of acceptance. i) this is worthless nonsense;
> ii) this is an interesting, but perverse, point of view, iii) this is true,
> but quite unimportant; iv) I always said so."
>
> --- J.B.S. Haldane
>
> _______________________________________________
> 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/20131212/edfb62ee/attachment.htm

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

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


End of Moses-support Digest, Vol 86, Issue 39
*********************************************

Tweet