Fifth Workshop on Hybrid Approaches to Translation HyTra-5

in conjunction with EAMT, Riga: June 1st 2016

Invited Speaker

Andy Way, Dublin City University, presented a talk about "Hybrid MT in Real-World Applications".

(cf. abstract, slides)

Panel Discussion

Panel discussion about Hybrid MT (more details in the program section), with Alex Fraser (LMU Munich), Maja Popovic (Humboldt University Berlin), Tony O'Dowd (KANTANMT), Andy Way (Adapt Centre, DCU) and Bogdan Babych (University of Leeds).

Fifth Workshop on Hybrid Approaches to Translation HyTra-5

The Fifth Workshop on Hybrid Approaches to Translation (HyTra-5), in conjunction with EAMT 2016, intended to continue developing and empowering the research agenda in the area of Hybrid MT. In the previous four editions already, prestigious invited speakers, full paper and poster sessions have allowed for fruitful, creative and interdisciplinary discussions, comparing and contrasting diverse ways to integrate different MT paradigms to improve the state-of-the-art in Machine Translation. This could be continued in the fifth workshop taking place in Riga. In addition to the proceedings, a contributed volume has been edited composed of papers selected from the first three editions of HyTra.

HyTrA motivates the cooperation and interaction between the different human components of such a highly interdisciplinary and multidisciplinary field, namely translators, engineers, computer scientists, mathematicians and linguists, as well as to foster innovation and creativity in the Hybrid Machine Translation research community.

Given the complementarity and mutual attractiveness of data-driven and rule-based MT, it is natural that the boundaries among them have narrowed. The question is what the combined architecture or architectures should look like. In the past few years, in the MT scientific community, the interest in hybridization and system combination has significantly increased.

Topics of interest

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)
  • 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 content
  • 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

Important dates:

6 May 2016: Paper submission deadline
12 May 2016: Notification to authors
20 May 2016: Camera-ready deadline
1 June 2016: Conference in Riga


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

Programme 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, Mexico City, Mexico
Josep Maria Crego, Systran, Paris, France
Kurt Eberle, Lingenio GmbH, Heidelberg, Germany
Cristina España, UPC, Barcelona
Christian Federmann, Microsoft Research, Seattle, USA
José R. Fonollosa, Universitat Politècnica de Catalunya, Barcelona, Spain
Maxim Khalilov, Berlin, Germany
Udo Kruschwitz, University of Essex, UK
Patrik Lambert, WebInterpret, 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, Athens, Greece
Jörg Tiedemann, University of Uppsala, Sweden
Grigori Sidorov, Instituto Politécnico Nacional, Mexico

The official Hytra 5 Workshop Homepage