|Monday, 28th May
|Opening of the Conference: welcome address by Manuel Palomar Sanz (President of the Universitat d'Alacant), Pedro Pernías Peco (Director-General for Telecommunications and Information Technologies, Generalitat Valenciana), Marina Campello Herrero (Alacant City Tourist Board), Mikel L. Forcada (President of the European Association for Machine Translation)
|Duygu Ataman, Mattia Antonino Di Gangi and Marcello Federico. “Compositional Source Word Representations for Neural Machine Translation” (research track)
|Mattia A. Di Gangi and Marcello Federico. “Deep Neural Machine Translation with Weakly-Recurrent Units” (research track)
|Alberto Poncelas, Dimitar Shterionov, Andy Way, Gideon Maillette de Buy Wenniger and Peyman Passban. “Investigating Backtranslation in Neural Machine Translation” (research track)
|Nisarg Jhaveri, Manish Gupta and Vasudeva Varma. “Translation Quality Estimation for Indian Languages” (research track)
|M. Amin Farajian, Nicola Bertoldi, Matteo Negri, Marco Turchi and Marcello Federico. “Evaluation of Terminology Translation in Instance-Based Neural MT Adaptation” (research track)
|Barry Haddow. “The WMT Shared Tasks”
|Best Thesis Award
|Poster Boaster (research and user tracks)
|Poster Session (research and user tracks)
|Dinner at Santa Bàrbara Castle (included with the registration fee; additional details will be provided during the conference)
|Tuesday, 29th May
|Keynote speech: “Human-Centred Translation Technology”. Dr. Sharon O'Brien, School of Applied Language and Intercultural Studies, Dublin City University.
|Poster Boaster (project/product track)
|Poster Session (project/product track)
|Xutai Ma, Ke Li and Philipp Koehn. “An Analysis of Source Context Dependency in Neural Machine Translation” (research track)
|Bram Bulté, Tom Vanallemeersch and Vincent Vandeghinste. “M3TRA: Integrating TM and MT for Professional Translators” (research track)
|Nora Aranberri and Jose A. Pascual. “Towards a Post-Editing Recommendation System for Spanish-Basque Machine Translation” (research track)
|EAMT General Assembly
|Dinner at Ocean Race Club (included with the registration fee; additional details will be provided during the conference)
|Wednesday, 30th May
|Sandipan Dandapat and Christian Federmann. “Iterative Data Augmentation for Neural Machine Translation: a Low Resource Case Study for English-Telugu” (user track)
|Nicholas Ruiz, Srinivas Bangalore and John Chen. “Bootstrapping Multilingual Intent Models via Machine Translation for Dialog Automation” (user track)
|Mara Chinea-Rios, Germán Sanchis-Trilles and Francisco Casacuberta. “Creating the Best Development Corpus for Statistical Machine Translation Systems” (research track)
|Meriem Beloucif and Dekai Wu. “SRL for Low Resource Languages Isn't Needed for Semantic SMT” (research track)
|Morgan O'Brien. “Toward Leveraging Gherkin Controlled Natural Language and Machine Translation for Global Product Information Development” (user track)
|Tanja Schmidt and Lena Marg. “How to Move to Neural Machine Translation for Enterprise-Scale Program – An Early Adoption Case Study” (user track)
|Introduction to the Translators Track Session
|Poster Boaster (translators track)
|Poster Session (translators track)
|Round Table (translators track): Celia Rico, Universidad Europea; Anna Zaretskaya, TransPerfect; Enrique Cillero, Cillero & de Motta
|Closing of the Conference
The conference proceedings are published as a single digital volume: Proceedings of the 21st Annual Conference of the European Association for Machine Translation (2018) Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović, Celia Rico, André Martins, Joachim Van den Bogaert, Mikel L. Forcada, editors. ISBN: 978-84-09-01901-4. Retrieved from http://eamt2018.dlsi.ua.es/proceedings-eamt2018.pdf.
This is the list of all the accepted papers grouped according to their track and modality (talk or poster).
EAMT 2018 will take place in the building Edifici d'Òptica i Optometria at the Universitat d'Alacant main campus.
By tramway: line 2 of the tramway (called Tram) connects the University with the city centre. Tramway has two main underground stations in the city centre: Alicante-Luceros Square and Mercado. You can check the timetables for each stop at their website. There is a service every 15 minutes and the journey takes 30 minutes; you have to get off at station Universitat. The conference venue is 6 minutes walk from Universitat in building 38 – Escuela Universitaria de Óptica (walking path).
By bus: the university can be easily reached by bus from the city centre. Line 24 has a service every 10 minutes from 6:30 to 22:30. It has many bus stops in the city centre, you can check which is the most convenient for you in their interactive map. One convenient stop is San Vicente, 20. The journey takes about 25 minutes and you have to take off at Alicante, 87. The conference venue is 8 minutes walk from Alicante, 87 in building 38 — Escuela Universitaria de Óptica (walking path).
Pangeanic is an innovation-driven private company dedicated to machine translation, software translation, post-editing and localization which falls within the small and medium enterprise category. It provides cutting-edge MT services ranging from customized machine-translation developments, online translation of customer reviews and background MT.
STAR offers custom solutions for your global product communication needs with tools and services in the areas of information management, technical documentation, translation, electronic publication, e-learning, and workflow automation. With more than 30 years of experience, STAR lets you make the most of your information in real-time, in any medium or technology, in any language, anytime, anywhere.
text&form is an experienced and innovative language services provider, headquartered in Berlin with offices in Canada and the UK. We are an official SAP Language Services and Language Consultancy Partner, and also offer technical translation, marketing translation, and multimedia localization services.
Vicomtech is an applied research centre specialising in advanced interaction technologies, computer vision, data analytics, computer graphics and language technologies. It aims to respond to the innovation requirements of companies and institutions by conducting applied research and developing multimedia visual interaction and communications technologies. Vicomtech complements and closely collaborates with industry, universities and other technology centres.
Apertium is a free/open-source machine translation platform providing: a language-independent engine, tools to manage language data, and data for more than 40 languages. You can be part of Apertium: improve the engine or the tools or develop language data.
Linguaserve, company providing linguistic solutions and services since 2000, operates and integrates automatic translation since 2004 in a customized way for the needs of each client. In its industry, it has been rated amongst the five biggest companies of Southern Europe (Common Sense Advisory 2017).
Prompsit is a language technology provider with a strong focus on custom machine translation (MT) services and related technologies such as corpora curation. It was created as a spin-off of the Transducens research group (University of Alacant, Spain) in 2006 along with the creation of the Apertium free/open-source MT platform in 2006.
Unbabel is an enterprise platform which enables multilingual communication across 28 languages. Unlike general purpose machine translation, Unbabel’s combination of artificial intelligence, together with a crowd of 50,000 and sophisticated domain adaptation enables human-quality translations that remove language barriers between companies and their customers.
MultiLingual is the magazine connecting global business and the language industry. It covers topics ranging from technical internationalization to project management to language histories in industries as varied as medical devices and games.
Although relatively young, the Universitat d'Alacant has a strong scientific and academic credibility which has allowed it to adapt to social changes and to the needs of its environment, leading a change of economic model based on research, innovation, entrepreneurship and actual transfer of knowledge.
The University Institute for Computer Research is an excellent and enthusiastic team of more than 105 researchers that promotes basic and applied research in the field of the computer science and technological development.
The Transducens research group from the Departament de Llenguatges i Sistemes Informàtics at the Universitat d'Alacant both contributes to the scientific progress and develops working products in the fields of translation technology, computer-aided translation, digital libraries and computer-aided education.
All prices include VAT. Fees vary depending on whether you are a member of the European Association for Machine Translation (EAMT) or not. If you are not currently a member of EAMT, you may apply for EAMT membership before registering for the conference and then proceed with an EAMT member conference fee.
Prices are lower until May 9th 2018. Online registration will close on May 21st 2018. You will be able to register at the venue on the days of the event if there are still spots available. Contact us first if you intend to register onsite.
Dinner, canteen lunch and coffee breaks are included in all fees. Accommodation is not included in any conference package and must be booked separately by each attendee.
|Early (until May 9th)
|Late (until May 21st)
|Regular, EAMT member
|Student, EAMT member
|Companion fee (banquet and reception only)
The European Association for Machine Translation (EAMT) invites everyone interested in machine translation, translation-related tools and resources to participate in this conference ― developers, researchers, users, professional translators and translation/localisation managers: anyone who has a stake in the vision of an information world in which language barriers and issues become less visible to the information consumer. We especially invite researchers to describe the state of the art and demonstrate their cutting-edge results, and professional MT users to share their experiences. Note also that individual translators are invited to share their insights in the use of MT and these will be addressed at a special track.
We expect to receive manuscripts in these four categories:
Long-paper submissions (up to 10 pages including references) are invited for reports of significant research results in any aspect of machine translation and related areas. Such reports should include a substantial evaluation component, or have a strong theoretical and/or methodological contribution where results and in-depth evaluations may not be appropriate. Papers are welcome on all topics in the areas of machine translation and translation-related technologies, including:
Papers should describe original work. They should emphasise completed work rather than intended work, and should indicate clearly the state of completion of the reported results. Where appropriate, concrete evaluation results should be included.
Papers should be anonymized, prepared according to the templates specified below, and no longer than 10 pages (including references); the resulting PDFs submitted to the EasyChair EAMT 2018 page (submission type: EAMT2018 Research).
Short-paper submissions (up to 6 pages, including references) are invited for reports on users' experiences with MT, be it as individual translators, in small- or medium-size business (SMB), in the enterprise, in the government, or in NGOs. Contributions are welcome on:
Papers should highlight problems and solutions in addition to describing MT integration process or project settings. Where solutions do not seem to exist, suggestions for MT researchers and developers should be clearly emphasised. For user papers produced by academics, we require co-authorship with the actual users. Papers should be formatted according to the templates specified below, no longer than 6 pages (including references), and submitted as PDF files to the EasyChair EAMT 2018 page (submission type: EAMT2018 User)
Abstract submissions (1 page) are invited to report new, interesting:
Abstracts should be formatted according to the templates specified below , no longer than 1 page (including references), and submitted as PDF files to the EasyChair EAMT 2018 page (submission type: EAMT2018 Products-Projects).
The use of machine translation by professional translators has an important social and economic impact due to the multilinguality of globalized societies. They deal with MT output in a wide variety of modalities (inside or outside CAT tools, post-editing it and interacting with it in some way or just as inspiration, as freelancers or as in-plant personnel, etc) and, quite often, the decision to use MT or not, and how to use it, is not taken by them or discussed with them in advance.
The machine translation community needs to hear the translators’ voice in a fresh and unfiltered way, and learn from their insights on issues such as the following:
Abstract submissions (1 page) are invited to report professional translators’ experiences with MT. We encourage professional translators to speak out freely, sincerely and in a proactive way, contributing to the debate with a challenging voice. Abstracts should be formatted according to the templates specified below, no longer than 1 page (including references), and submitted as PDF files to the EasyChair EAMT 2018 page (submission type: EAMT2018 Translator).
Accepted papers will be published in an electronic book of proceedings with an ISBN number. In addition, the best accepted papers will be invited to submit an extended version undergoing a lighter reviewing process, as regular papers in the Springer journal Machine Translation.
The conference will open with an invited talk by Sharon O'Brien (Dublin City University) on "Human-centred translation technology".
In addition to the invited talk, the programme of the research and user tracks will include oral presentations and poster sessions. Accepted papers may be assigned to an oral or poster session, but no differentiation will be made in the conference proceedings.
There will also be a special Translators’ track, which will mostly take place on Wednesday. It will be organized around selected, very short oral contributions by individual translators, and will end with a round table where the voice of individual translators will be heard along those of researchers, developers and companies using machine translation.
The EAMT Best Thesis Award 2018 for PhD theses submitted during 2017 will be awarded at the conference, together with a presentation of the winner’s work. Information for candidates to the award is available here. The deadline is the same as for the paper submission. Theses should be submitted to the EasyChair EAMT 2018 page (submission type: Thesis Award).