[Corpora-List] First CFP: HyTra-6 Sixth Workshop on Hybrid Approaches to Translation (in conjunction with COLING)

Marta Ruiz martaruizcostajussa at gmail.com
Tue Jul 12 08:41:38 CEST 2016


*HyTra-6: Sixth Workshop on Hybrid Approaches to Translation* <http://glicom.upf.edu/hytra6/>

The Sixth Workshop on Hybrid Approaches to Translation (HyTra-6), in conjunction with *COLING 2016*, intends to invite work contributions on integrating any type of data-driven and linguistic-based machine translation approaches. Nowadays, there are more paradigms competing in machine translation including statistical (phrase-based, hierarchical and syntax-based), neural-based and rule-based. Each of them has their own advantages and disadvantages which make it worth the research on hybridization, integration and/or combination of approaches. Given that academic and industry perspectives may differ on the opinion of which are the most suitable paradigms, HyTra gives a strong relevance to the participation of both in the workshop. The fact that machine translation is a highly interdisciplinary field (including engineers, computer scientists, mathematicians, translators, linguists…), specially in the research of hybridization, enriches the workshop in its discussions, proceedings, invited talks and, even, in one contributed volume published by Springer.

In this edition, HyTRA will specially focus on motivating the cooperation and interaction between the different human components, as well as to foster innovation and creativity in the Hybrid Machine Translation research community. That is why we encourage the participation of the different integrating fields (engineers, computer scientists, mathematicians, translators, linguists either from academy or industry) to contribute to our special call of shared task proposals.

Given the complementarity and mutual attractiveness of data-driven and rule-based MT, the appearance of new data-driven approaches (such as the neural-based one), the question is what the combined architecture should look like.

We will 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)

· bootstrapping rule-based systems from corpora

· extraction of dictionaries from parallel and comparable corpora

· induction of morphological, grammatical, and translation rules from corpora

· improving MT with statistical and rule-based computational linguistics methods (word sense disambiguation, information extraction, terminology mining, metaphor recognition, etc.)

· machine learning techniques for hybrid MT and complex data structures

· describing and using structural mappings between languages (e.g. tree-structures using synchronous/transduction grammars)

· system combination approaches such as multi-engine MT (parallel) or automatic post-editing (sequential)

· hybrid methods in spoken language translation

· heuristics for limiting the search space in hybrid MT

· translation of user generated contents

· alternative methods for the fair evaluation of the output of different types of MT systems (e.g. relying on linguistic criteria)

· use of word embeddings and continuous vector space representations in hybrid MT

· neural networks, deep learning and neural MT hybridization

· open source tools and free language resources for hybrid MT

· presentations of industrial hybrid MT systems and technologies which involve hybrid MT systems in commercial and professional applications

*Call for shared task proposals*

We solicit proposals for shared tasks relevant to hybrid translation with the potential to be conducted in future editions of the HyTra workshop series. Proposals should include:

1) A definition of the objectives of the shared task (e.g. user generated content translation) ; 2) A suggestion of a baseline system (if appropriate) ; 3) Data to conduct the shared task; 4) An evaluation measure

Proposals should be different from those conducted elsewhere. We particularly welcome proposals which motivate the MT industry to participate.

The proposals should be 2 pages long in the format required by the workshop. The best proposals will be published in the proceedings and discussed in a panel. The authors of convincing proposals will be invited to organize a shared task in conjunction with upcoming editions of the HyTra workshop series.

Please send your proposals to patrik.lambert at gmail.com

*Important Dates*

*Paper submission* September 25th, 2016

*Notification to authors* October 16th, 2016

*Camera-ready deadline* October 30th, 2016

*Workshop *December 11th, 2016

*Program Committee *

· Arianna Bisazza, University of Amsterdam, The Netherlands

· Bogdan Babych, University of Leeds, UK

· Rafael E. Banchs, Institute for Infocomm Research, Singapore

· Alexey Baytin, Yandex, Moscow, Russia

· Pierrette Bouillon, ISSCO/TIM/ETI, University of Geneva, Switzerland

· Marta R. Costa-jussa, UPC, Barcelona

· Josep Maria Crego, Systran, Paris, France

· Kurt Eberle, Lingenio GmbH, Heidelberg, Germany

· Cristina España, UPC, Barcelona

· Christian Federmann, Microsoft Research, Seattle, USA

· José A. R. Fonollosa, UPC, Barcelona

· Maxim Khalilov, Berlin, Germany

· Udo Kruschwitz, University of Essex, UK

· Patrik Lambert, Pompeu Fabra University, Barcelona, Spain

· Maite Melero, Pompeu Fabra University, Barcelona, Spain

· Reinhard Rapp, Universities of Aix-Marseille, France, and Mainz, Germany

· George Tambouratzis, Institute for Language and Speech Processing, Greece

· Jörg Tiedemann, University of Uppsala, Sweden

· Grigori Sidorov, Instituto Politécnico Nacional, Mexico

*Organizing Committee*

Patrik Lambert, Bogdan Babych, Kurt Eberle, Rafael E. Banchs, Reinhard Rapp and Marta R. Costa-jussà

*Contact*

Patrik Lambert (patrik.lambert at gmail.com) -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 24880 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20160712/339ad704/attachment.txt>



More information about the Corpora mailing list