Deep Machine Translation Workshop 2016

Lisbon, October 21, 2016



University of Lisbon, Rectorship Building, Conference Room (near Aula Magna)
Alameda da Universidade, 1649-004 Lisboa, Portugal

Google map

Workshop Program – October 21, 2016

Proceedings in printable form, with page numbers, ISBN, front matter etc. are available here.

09:00-09:15 Welcome (Jan Hajič, António Branco, Gertjan van Noord)
09:15-09:45 Rudolf Rosa, Martin Popel, Ondřej Bojar, David Mareček and Ondřej Dušek. Moses & Treex Hybrid MT Systems Bestiary
09:45-10:15 Natalia Klyueva and Vladislav Kubon. Incorporation of a valency lexicon into a TectoMT pipeline
10:15-10:45 Kiril Simov and Petya Osenova. A Hybrid Approach for Deep Machine Translation
10:45-11:15 Coffee Break
11:15-11:45 Eleftherios Avramidis, Vivien Macketanz, Aljoscha Burchardt, Jindrich Helcl and Hans Uszkoreit. Deeper Machine Translation and Evaluation for German
11:45-12:15 Sophie Arnoult and Khalil Simaan. Factoring Adjunction in Hierarchical Phrase-Based SMT
12:15-12:45 Mikel Artetxe, Gorka Labaka, Chakaveh Saedi, João Rodrigues, João Silva, António Branco and Eneko Agirre. Adding syntactic structure to bilingual terminology for improved domain adaptation
12:45-13:00 Final discussion, future workshops

Call for papers

This is the second workshop on “Deep Machine Translation“, the first being held in Prague in 2015 ( Its aim is to bring together researchers and students working on machine translation approaches and technology using “deep understanding” (not necessarily using Deep Neural Networks, as the name might suggest, but certainly not excluding them either). Adding “more linguistics” has long been considered as a possible way to boost quality of current, mainly (PB)SMT-based systems. However, there are many ways to do so, and it was felt a forum is needed where experience can be shared among people working on such systems.

Papers on original and unpublished research are welcome on any of the topics listed above in general, and specifically on any of the following:

  • General approaches to the use of linguistic knowledge for Machine Translation
  • Contrast and comparison of Deep linguistic methods vs. Deep neural networks for MT
  • Semantics for Machine Translation
  • Combination of statistical and “manual” approaches to Machine Translation, hybrid systems
  • Innovative use of manually built lexical resources in Machine Translation (monolingual, bilingual)
  • Deep linguistic representation of meaning / semantics, including semantic graphs, logical representation, temporal and spatial representation and grounding
  • Deep linguistic analysis and generation
  • Joint linguistic and distributional modeling (analysis, generation, transfer)
  • Analysis, generation and transfer using graph-based meaning representation
  • Incorporating coreference, named entity recognition, words sense disambiguation, or any other linguistically motivated features into the MT chain
  • Multilingual question-answering and CLIR approaches, including specific methods for query translation and query matching in a multilingual setting
  • Evaluation methods for standard text translation, query translation, and CLIR



Submissions must be made through the easychair system at Please see below for the important dates.



Call for papers released: May 30, 2016
Submission deadline: September 16, 2016 (extended from 11th)
Workshop date: October 21, 2016


Instructions for authors

Templates and Submission page (also for final manuscripts): templatessubmission page

The maximum submission length is 8 pages (A4), plus two extra pages for references, following a one-column ACL-like format, as specified below.

Papers shall be submitted in English. As the reviewing will be double-blind, papers must be anonymized with regard to the authors and/or their institution (no author-identifying information on the title page nor anywhere in the paper), including referencing style as usual. Authors should also ensure that identifying meta-information is removed from files submitted for review. Papers must conform to official DMTW 2015 style guidelines (see above in templates). Submission and reviewing will be managed online by the EasyChair system. The only accepted format for submitted papers is in Adobe’s PDF.

Submissions must be uploaded on the EasyChair system by the submission deadlines; submissions after that time will not be reviewed.

Papers that are being submitted in parallel to other conferences or workshops must indicate this on the title page. Papers that contain significant overlap with previously published work must also signal that.

Papers will be published online by the time of the Workshop, assigned an ISBN as regular proceedings published by the UFAL / Charles University publishing house, and listed in the ACL Anthology.

Mode of presentation will be decided by the Program Committee based on the submitted papers – either as an oral presentation or as a poster, based on suitability for the given presentation mode, not quality – all papers will be given the same space in the proceedings, and there will be no distinction in the proceedings between research papers presented orally vs. as posters. Papers will be reviewed by at least three members of the Program Committee.



Jan Hajič, Charles University in Prague
Gertjan van Noord, University of Groningen
António Branco, University of Lisbon

DeepMT’2016 workshop is organized and supported by the QTLeap project.


Program Committee

Jan Hajič, Charles University in Prague (Chair)
Gertjan van Noord, University of Groningen (Co-chair)
António Branco, University of Lisbon (Co-chair)
Aljoscha Burchardt, DFKI
Dekai Wu, The Hong Kong University of Science and Technology
Deyi Xiong, Soochow University
Eneko Agirre, University of the Basque Country
Eva Hajicova, Charles University in Prague
João Silva, University of Lisbon
Khalil Sima’an, University of Amsterdam
Kiril Simov, Bulgarian Academy of Sciences
Martin Popel, Charles University in Prague
Petya Osenova, Bulgarian Academy of Sciences
Rosa Del Gaudio, Higher Functions