CORDIS

EU research results

CORDIS

Health in my Language

Fact Sheet

Result in Brief

Reporting

Results

Objective

To an ever-increasing extent, web-based services are providing a frontline for healthcare information in Europe. They help citizens find answers to their questions and help them understand and find the local services they need. However, due to the number of languages spoken in Europe, and the mobility of its population, there is a high demand for these services to be available in many languages. In order to satisfy this demand, we need to rely on automatic translation, as it is infeasible to manually translate into all languages requested. The aim of HimL is to use recent advances in machine translation to create and deploy a system for the automatic translation of public health information, with a special focus on meaning preservation. In particular, we will include recent work on domain adaptation, translation into morphological rich languages, terminology management, and semantically enhanced machine translation to build reliable machine translation for the health domain. The aim will be to create usable, reliable, fully automatic translation of public health information, initially testing with translation from English into Czech, Polish, Romanian and German. In the HimL project we will iterate cycles of incorporating improvements into the MT systems, with careful evaluation and user acceptance testing.

Programme(s)

H2020-EU.2.1.1.4. - Content technologies and information management: ICT for digital content, cultural and creative industries

Topic(s)

ICT-17-2014 - Cracking the language barrier

Call for proposal

H2020-ICT-2014-1

See other projects for this call

Funding Scheme

IA - Innovation action

Coordinator

THE UNIVERSITY OF EDINBURGH

Address

Old College, South Bridge
Eh8 9yl Edinburgh

United Kingdom

Activity type

Higher or Secondary Education Establishments

EU Contribution

€ 785 083,75

Website

Contact the organisation

Participants (5)

Sort alphabetically

Sort by EU Contribution

Expand all

UNIVERZITA KARLOVA

Czechia

EU Contribution

€ 475 000

LUDWIG-MAXIMILIANS-UNIVERSITAET MUENCHEN

Germany

EU Contribution

€ 510 875

LINGEA SRO

Czechia

EU Contribution

€ 237 562,50

NHS 24 (SCOTLAND)

United Kingdom

EU Contribution

€ 547 425

THE COCHRANE COLLABORATION

United Kingdom

EU Contribution

€ 393 625

Project information

HimL

Grant agreement ID: 644402

Project website

Start date

1 February 2015
End date

31 January 2018

Funded under:

H2020-EU.2.1.1.4.

Overall budget:

€ 3 071 897,77
EU contribution

€ 2 949 571,25

Coordinated by:

THE UNIVERSITY OF EDINBURGH

United Kingdom

DE EN ES FR IT PL

Pushing back the boundaries of machine translation for health

EU researchers have brought us a step closer to fully-automated machine translation with a neural-based system capable of translating texts on public health from English into Czech, German, Polish and Romanian.

DIGITAL ECONOMY

Online information is often only available in a few languages as organisations cannot afford to translate it into more. But researchers from the EU-funded Health in My Language, or HimL project, have brought the prospect of fully automated machine translation a step closer, by working with Scottish and international public health organisations to produce a system adapted for the health domain. “Immigrant communities may have limited command of the local language – they need information about local health services but it is not available in their language,” says Barry Haddow, project co-ordinator and senior researcher in informatics at the University of Edinburgh. “Information about best practices in health care, resulting from recent research, is mainly disseminated in English but consumers would like to access new meta-analyses in their own language.” Deep learning The HimL team researched quality improvements in machine translation and incorporated these into a new system able to work from English into Czech, German, Polish and Romanian. It started using a syntactic or phrase-based approach, but quickly moved to neural machine translation (NMT), an approach based on deep learning which emerged during the life of the project. New versions were released each year for use by project partners NHS 24, the Scottish national health service, and Cochrane, an NGO that facilitates access to the latest research on health matters. The results were carefully evaluated using user surveys and application-focused testing. The improvements were made in three main areas; domain adaptation or tuning the translation to the specific terminology of public health; semantics or ensuring accuracy of translation; morphology or making sure morphological variants are correctly produced. “English doesn’t have a lot of morphology, but a lot of languages in Europe, such as Czech and Polish, do – they have different verb and nouns forms according to use and, if you get it wrong, this can change the meaning of the text,” says Dr Haddow. Users were asked to rank the results produced by HimL compared to a well-known online system. “Our systems were able to offer better results in all language pairs,” says Dr Haddow, “although the extremely high quality required by NHS 24 and Cochrane users means that we are not yet able to automate translation completely.” Less human intervention The team also looked at how well the HimL systems performed when combined with post-editing – this approach uses machine translation to produce a rough first version, then gets a human translator to edit the result. “Cochrane showed that post-editing using the HimL system in the MateCat tool was 30-40 % faster than translation from scratch for all languages except for Polish,” says Dr Haddow. “We were able to reduce the amount of human intervention by between 30–50% to produce as good a translation as we would have achieved with the fully human approach.” Other outputs include the UFAL medical corpus, a standard data set for training systems to deal with medical texts. It covers eight European language pairs, including the HimL ones. Analysing the output of NMT showed that problems present in earlier systems have now been largely overcome, but that these systems are still prone to omitting important information or adding incorrect information. “To counter this we use a technique called "reconstruction", where the source should be reconstructable from the output,” says Dr Haddow, “we have also shown how to improve NMT using high quality dictionaries and how to incorporate semantic and syntactic information from external tools.”

Keywords

HimL, machine translation, health domain, domain adapation, semantics, morphology, morphologically-rich languages, post-editing

Project information

HimL

Grant agreement ID: 644402

Project website

Start date

1 February 2015
End date

31 January 2018

Funded under:

H2020-EU.2.1.1.4.

Overall budget:

€ 3 071 897,77
EU contribution

€ 2 949 571,25

Coordinated by:

THE UNIVERSITY OF EDINBURGH

Discover other articles in the same domain of application

Results in Brief

Talking over the computer

7 February 2011

Results in Brief

Silicon hybrids for better optics and electronics

25 October 2010

Results in Brief

Smart tracking for life

25 October 2010

Periodic Reporting for period 1 - HimL (Health in my Language)

Reporting period: 2015-02-01 to 2016-07-31

Summary of the context and overall objectives of the project

The goal of the HimL project is to increase timely access to important public health information by making
it available to consumers in their own language. We do this using high quality machine translation
optimised for semantic fidelity. This addresses two distinct but related problems:

1) A large proportion of public health information is local: While general information about diabetes may
be available in Polish, Romanian or Urdu, what a Polish speaker in Aberdeen, or a Romanian speaker in
Edinburgh or an Urdu speaker in Glasgow needs is local information about diabetes services and care,
but in their own language.
2) Best practice in public health care can change, as a result of new research studies and/or meta-analyses.
Recommendations in line with best practice need to be made available to consumers, as soon as possible,
through timely, accurate translation into their own language.

The first problem reflects the translation needs of national and regional public health services such as our partner
NHS 24, while the second reflects the translation needs of trans-national health information providers such as
our partner COCHRANE. We will address these needs by applying recent advances in machine translation (MT)
to make their texts available in a timely fashion to a much wider range of language communities.
Fully automatic translation systems will be created to translate public health information from English into
Czech, German, Polish and Romanian. This particular set of languages have been chosen because of the needs
of our user partners, and because they cover the three major families of European languages (Slavic, Germanic
and Romance). What is more, all four of these languages are classified as having “weak or no support” or
“fragmentary support” according to the META-NET language white papers.

The innovations in MT that we adapt, integrate and apply in the project include:
1) Domain adaptation to build MT systems tailored to the public health domain in terms of terminology,
register and reading level;
2) Semantically–aware MT to improve translation fidelity, along with semantic evaluation to
tune the systems for fidelity and serve as specific automated progress metrics;
3) Morphology prediction to translate from morphologically impoverished English to the morphologically
richer target languages considered in this project.

Through the life of the project we will transfer the above improvements in MT from lab-based systems, to live
on-line health care services which are highly trusted and have large numbers of users. This project will allow
these multi-lingual services to expand coverage to more content and to new languages, becoming more widely
useful to European healthcare consumers. The HimL project places a great deal of emphasis on the deployment,
evaluation and dissemination of current MT research and the user partners are committed to proving both the
usefulness and the impact of the project, by running extensive user acceptance testing, and collecting web traffic
and web user feedback.

In summary, the implementational objectives of the project are:
1) Collate the latest research on high accuracy machine translation, to develop systems which are measur-
ably more reliable, for our particular domain, than baseline state-of-the-art models.
2) Deploy translation engines as services with a simple interface and scalable performance.
3) Integrate translation functionality seamlessly into the content management workflow of two high-profile
on-line healthcare information providers.
4) Add translation functionality to their websites, carefully managing user expectation and evaluating user
satisfaction.
5) Comprehensively measuring the impact of this new functionality on the services provided by NHS24 and
COCHRANE .

By achieving these more concrete objectives we will be taking steps towards achieving our global objec-
tives:
1) Increase the accuracy of machine translation, making it more reliable and more wi

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Logo

Project information

HimL

Grant agreement ID: 644402

Project website

Start date

1 February 2015
End date

31 January 2018

Funded under:

H2020-EU.2.1.1.4.

Overall budget:

€ 3 071 897,77
EU contribution

€ 2 949 571,25

Coordinated by:

THE UNIVERSITY OF EDINBURGH

Deliverables

Documents, reports (16)

Initial report on inflection and word formation

This report will describe our initial work on inflection and word formation. (T3.2-3.6)

Common Morphology Interface description

This deliverable will define a common interface to morphological resources. (T3.1)

Test sets for HimL languages

Create domain specific test sets for each language pair, to be used for automated testing during system development. (T5.1)

Final report on employing semantic role labelling and shallow proxies for negation and fidelity checking in machine translation

This report will summarise all our work on semantics as applied to machine translation. (T2.1, T2.2, T2.3)

Intermediate report on inflection and word formulation

This deliverable will update our initial report on inflection and word formation. (T3.2-3.6)

Initial report on employing semantic role labelling and fidelity checking in machine translation

This report will describe our initial approach to applying semantic role labelling in machine translation. (T2.1)

Report on Mining Terminology Translations from Non-Parallel Data

This report will describe the mining of terminology dictionaries from resources such as Wikipedia. (T1.3)

Report on seminar on automatic translation in the health domain

This deliverable consists of organising a seminar on machine translation for the health domain. (T6.3)

Intermediate report on employing semantic role labelling and fidelity checking in machine translation

This report will update the initial report on semantic role labelling, and include further research on negation and fidelity checking in machine translation. (T2.1, T2.2, T2.3)

Final report on inflection and word formation

This report will summarise all our work on inflection and word formation. (T3.2-3.6)

Report on first year's MT evaluation

This report will describe the first year's evaluation of the research performed in the other work packages, and of the systems deployed by the industrial partners. (T5.4, T5.5)

Report on third year's MT evaluation

This report will describe the final year's evaluation of the research performed in the other work packages, and of the systems deployed by the industrial partners. (T5.4, T5.5)

Report on second year's MT evaluation

This report will describe the second year's evaluation of the research performed in the other work packages, and of the systems deployed by the industrial partners. (T5.4, T5.5)

Report on preliminary semantic evaluation metric

This report will describe our initial work on developing a semantic evaluation metric. (T5.2, T5.3)

Report on integrated semantic evaluation metric

This report will describe our final approach to human and automatic evaluation of semantic accuracy. (T5.2, T5.3)

Report on Building Translation Systems for Public Health Domain

This report will describe the process of collecting data and building of translation systems for the public health domain, using standard parallel data and domain specific resources such as ontologies. (T1.1)

Websites, patent fillings, videos etc. (1)

Publications

Conference proceedings (52)

Neural Networks for Negation Cue Detection in Chinese

Author(s): He, Hangfeng and Fancellu, Federico and Webber, Bonnie

Published in: Proceedings of the Workshop Computational Semantics Beyond Events and Roles, 2017

CimS - The CIS and IMS Joint Submission to WMT 2015 addressing morphological and syntactic differences in English to German SMT

Author(s): Fabienne Cap and Marion Weller and Anita Ramm and Alexander Fraser

Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation (WMT), 2015

A Joint Dependency Model of Morphological and Syntactic Structure for Statistical Machine Translation

Author(s): Rico Sennrich and Barry Haddow

Published in: Proceedings of EMNLP, 2015

Results of the WMT15 Metrics Shared Task

Author(s): Stanojević, Miloš and Kamran, Amir and Koehn, Philipp and Bojar, Ondřej

Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015

Planting Trees in the Desert: Delexicalized Tagging and Parsing Combined

Author(s): Daniel Zeman and David Mareček and Zhiwei Yu and Zdeněk Žabokrtský

Published in: Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation, PACLIC 30, 2016

The University of Edinburgh's Neural MT Systems for WMT17

Author(s): Sennrich, Rico and Birch, Alexandra and Currey, Anna and Germann, Ulrich and Haddow, Barry and Heafield, Kenneth and Miceli Barone, Antonio Valerio and Williams, Philip

Published in: Proceedings of the Second Conference on Machine Translation, 2017

A Neural Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation

Author(s): Maria N\vadejde and Alexandra Birch and Philipp Koehn

Published in: Proceedings of IWSLT, 2016

What a Transfer-Based System Brings to the Combination with PBMT

Author(s): Aleš Tamchyna and Ondřej Bojar

Published in: Proceedings of the Fourth Workshop on Hybrid Approaches to Translation (HyTra), 2015

Mixed-Domain vs. Multi-Domain Statistical Machine Translation

Author(s): Matthias Huck and Alexandra Birch and Barry Haddow

Published in: Proceedings of MT Summit, 2015

Results of the WMT16 Metrics Shared Task

Author(s): Ondřej Bojar and Yvette Graham and Amir Kamran and Miloš Stanojević

Published in: Proceedings of the First Conference on Machine Translation (WMT). Volume 2: Shared Task Papers, 2016

Results of the WMT16 Tuning Shared Task

Author(s): Bushra Jawaid and Amir Kamran and Miloš Stanojević and Ondřej Bojar

Published in: Proceedings of the First Conference on Machine Translation ({WMT}). Volume 2: Shared Task Papers, 2016

CUNI-LMU Submissions in WMT2016: Chimera Constrained and Beaten

Author(s): Aleš Tamchyna and Roman Sudarikov and Ondřej Bojar and Alexander Fraser

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

Target-side Generation of Prepositions for SMT

Author(s): Marion Weller and Alexander Fraser and Sabine Schulte im Walde

Published in: Proceedings of EAMT 2015, 2015

Using Term Position Similarity and Language Modeling for Bilingual Document Alignment

Author(s): Le Thanh and Hoa Vu Throng and Jonathan Oberländer and Ondřej Bojar

Published in: Proceedings of the First Conference on Machine Translation ({WMT}). Volume 2: Shared Task Papers, 2016

CUNI in WMT15: Chimera Strikes Again

Author(s): Ondřej Bojar and Aleš Tamchyna

Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015

Edinburgh's Syntax-Based Systems at WMT 2015

Author(s): Philip Williams and Rico Sennrich and Maria Nadejde and Matthias Huck and Philipp Koehn

Published in: Proceedings of WMT, 2015

Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification

Author(s): Wetzel, Dominikus

Published in: Proceedings of the First Conference on Machine Translation (WMT16), 2016

Labeled Morphological Segmentation with Semi-Markov Models

Author(s): Ryan Cotterell and Thomas Müller and Alexander Fraser and Hinrich Schütze

Published in: Proceedings of the Nineteenth Conference on Computational Natural Language Learning (CoNLL), 2015

A Framework for discriminative Rule Selection in Hierarchical Moses

Author(s): Fabienne Braune and Alexander Fraser and Hal Daumé III and Aleš Tamchyna

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

Target-Side Context for Discriminative Models in Statistical Machine Translation

Author(s): Aleš Tamchyna and Alexander Fraser and Ondřej Bojar and Marcin Junczys-Dowmunt

Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016

Deep architectures for Neural Machine Translation

Author(s): Miceli Barone, Antonio Valerio and Helcl, JindĹ™ich and Sennrich, Rico and Haddow, Barry and Birch, Alexandra

Published in: Proceedings of the Second Conference on Machine Translation, 2017

Producing Unseen Morphological Variants in Statistical Machine Translation

Author(s): Huck, Matthias and Tamchyna, AleĹˇ and Bojar, OndĹ™ej and Fraser, Alexander

Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, 2017

Edinburgh Neural Machine Translation Systems for WMT 16

Author(s): Rico Sennrich and Barry Haddow and Alexandra Birch

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

Addressing Problems across Linguistic Levels in SMT: Combining Approaches to Model Morphology, Syntax and Lexical Choice

Author(s): Marion Weller-Di Marco and Alexander Fraser and Sabine Schulte im Walde

Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (Short Paper), 2017

Translating negation: A manual error analysis

Author(s): Federico Fancellu and Bonnie Webbe

Published in: Extra-Propositional Aspects of Meaning (ExProM) in Computational Linguistics Workshop, 2015

Modeling Target-Side Inflection in Neural Machine Translation

Author(s): Tamchyna, AleĹˇ and Weller-Di Marco, Marion and Fraser, Alexander

Published in: Proceedings of the Second Conference on Machine Translation (WMT), 2017

The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016

Author(s): Matthias Huck and Alexander Fraser and Barry Haddow

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

If You Even Don't Have a Bit of Bible: Learning Delexicalized POS Taggers

Author(s): Zhiwei Yu and David Mareček and Zdeněk Žabokrtský and Daniel Zeman

Published in: Proceedings of the 10th International Conference on Language Resources and Evaluation ({LREC} 2016), 2016

Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation

Author(s): Fabienne Braune and Nina Seemann and Alexander Fraser

Published in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015

Predicting Target Language CCG Supertags Improves Neural Machine Translation

Author(s): Nadejde, Maria and Reddy, Siva and Sennrich, Rico and Dwojak, Tomasz and Junczys-Dowmunt, Marcin and Koehn, Philipp and Birch, Alexandra

Published in: Proceedings of the Second Conference on Machine Translation, 2017

Annotating tense, mood and voice for English, French and German

Author(s): Anita Ramm and Sharid Loaiciga and Annemarie Friedrich and Alexander Fraser

Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), demonstration session, 2017

Modeling Complement Types in Phrase-Based SMT

Author(s): Marion Weller-Di Marco and Alexander Fraser and Sabine Schulte im Walde

Published in: Proceedings of the First Conference of Machine Translation (WMT2016), 2016

The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT~2015

Author(s): Barry Haddow and Matthias Huck and Alexandra Birch and Nikolay Bogoychev and Philipp Koehn

Published in: Proceedings of WMT, 2015

How to Account for Idiomatic German Support Verb Constructions in Statistical Machine Translation

Author(s): Fabienne Cap and Manju Nirmal and Marion Weller and Sabine Schulte im Walde

Published in: Proceedings of the 11th Workshop on Multiword Expressions at NAACL, 2015

Universal Dependencies to Logical Form with Negation Scope

Author(s): Fancellu, Federico and Reddy, Siva and Lopez, Adam and Webber, Bonnie

Published in: Proceedings of the Workshop Computational Semantics Beyond Events and Roles, 2017

Edinburgh's Statistical Machine Translation Systems for WMT16

Author(s): Philip Williams and Rico Sennrich and Maria Nadejde and Matthias Huck and Barry Haddow and Ondřej Bojar

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

Linguistic Input Features Improve Neural Machine Translation

Author(s): Rico Sennrich and Barry Haddow

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

HUME: Human UCCA-Based Evaluation of Machine Translation

Author(s): Birch, Alexandra and Abend, Omri and Bojar, OndĹ™ej and Haddow, Barry

Published in: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016

Nematus: a Toolkit for Neural Machine Translation

Author(s): Sennrich, Rico and Firat, Orhan and Cho, Kyunghyun and Birch, Alexandra and Haddow, Barry and Hitschler, Julian and Junczys-Dowmunt, Marcin and LĂ¤ubli, Samuel and Miceli Barone, Antonio Valerio and Mokry, Jozef and Nadejde, Maria

Published in: Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017

LMU Munich's Neural Machine Translation Systems for News Articles and Health Information Texts

Author(s): Huck, Matthias and Braune, Fabienne and Fraser, Alexander

Published in: Proceedings of the Second Conference on Machine Translation (WMT), 2017

Health in my Language: evaluation of health domain adapted machine translation for Cochrane Reviews.

Author(s): Ried, Juliane

Published in: Challenges to evidence-based health care and Cochrane. Abstracts of the 24th Cochrane Colloquium, 2016

Copied Monolingual Data Improves Low-Resource Neural Machine Translation

Author(s): Currey, Anna and Miceli Barone, Antonio Valerio and Heafield, Kenneth

Published in: Proceedings of the Second Conference on Machine Translation, 2017

Health in my Language: health domain adapted machine translation as a means to tackle the resource issues for translation.

Author(s): Juliane Ried

Published in: Filtering the information overload for better decisions. Abstracts of the 23rd Cochrane Colloquium, 2015

Target-side Word Segmentation Strategies for Neural Machine Translation

Author(s): Huck, Matthias and Riess, Simon and Fraser, Alexander

Published in: Proceedings of the Second Conference on Machine Translation (WMT), 2017

Modeling verbal inflection for English to German SMT

Author(s): Anita Ramm and Alexander Fraser

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

Detecting negation scope is easy, except when it isn't

Author(s): Fancellu, Federico and Lopez, Adam and Webber, Bonnie and He, Hangfeng

Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, 2017

Findings of the WMT 2017 Biomedical Translation Shared Task

Author(s): Jimeno Yepes, Antonio and Neveol, Aurelie and Neves, Mariana and Verspoor, Karin and Bojar, Ondrej and Boyer, Arthur and Grozea, Cristian and Haddow, Barry and Kittner, Madeleine and Lichtblau, Yvonne and Pecina, Pavel and Roller, Roland and Rosa, Rudolf and Siu, Amy and Thomas, Philippe and Trescher, Saskia

Published in: Proceedings of the Second Conference on Machine Translation, 2017

Joint Lemmatization and Morphological Tagging with Lemming

Author(s): Thomas Müller and Ryan Cotterell and Alexander Fraser and Hinrich Schütze

Published in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015

Results of the WMT15 Tuning Shared Task

Author(s): Miloš Stanojević and Amir Kamran and Ondřej Bojar

Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015

Neural Networks For Negation Scope Detection

Author(s): Federico Fancellu and Adam Lopez and Bonnie Webber

Published in: The 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), 2016

The QT21/HimL Combined Machine Translation System

Author(s): Jan-Thorsten Peter and Tamer Alkhouli and Hermann Ney and Matthias Huck and Fabienne Braune and Alexander Fraser and Aleš Tamchyna and Ondřej Bojar and Barry Haddow and Rico Sennrich and Frédéric Blain and Lucia Specia and Jan Niehues and Alexandre Allauzen and Lauriane Aufrant and Franck Burlot and Elena Knyazeva and Thomas Lavergne and Francois Yvon and Joachim Daiber and Marcis Pinnis

Published in: Proceedings of First Conference on Machine Translation (WMT2016), 2016

Predicting Prepositions for SMT (extended abstract)

Author(s): Marion Weller and Alexander Fraser and Sabine Schulte im Walde

Published in: Proceedings of the 9th Workshop on Syntax, Semantics and Structure in Statistical Translation at NAACL, 2015

Peer reviewed articles (3)

TmTriangulate: A Tool for Phrase Table Triangulation

Author(s): Tam Hoang and Ondřej Bojar

Published in: The Prague Bulletin of Mathematical Linguistics, 2015, ISSN 1804-0462

Evaluating health-domain adapted machine translation for Cochrane plain language summaries.

Author(s): Ried, Juliane and Hassan Hayley and de Haan, Sylvia de and Wood, Julie

Published in: Cochrane Database of Systematic Reviews, 2017, ISSN 1361-6137

CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered

Author(s): Ondřej Bojar and Ondřej Dušek and Tom Kocmi and Jindřich Libovický and Michal Novák and Martin Popel and Roman Sudarikov and Dušan Variš

Published in: Lecture Notes in Computer Science, 2016, ISSN 0302-9743

Project information

HimL

Grant agreement ID: 644402

Project website

Start date

1 February 2015
End date

31 January 2018

Funded under:

H2020-EU.2.1.1.4.

Overall budget:

€ 3 071 897,77
EU contribution

€ 2 949 571,25

Coordinated by:

THE UNIVERSITY OF EDINBURGH

Project information

HimL

Grant agreement ID: 644402

Project website

Start date

1 February 2015
End date

31 January 2018

Funded under:

H2020-EU.2.1.1.4.

Overall budget:

€ 3 071 897,77
EU contribution

€ 2 949 571,25

Coordinated by:

THE UNIVERSITY OF EDINBURGH

Download

PDF

XML

Last update: 20 March 2017

Record number: 194204

CORDIS

Objective

Coordinator

Participants (5)

Project information

Pushing back the boundaries of machine translation for health

Keywords

Project information

Discover other articles in the same domain of application

Periodic Reporting for period 1 - HimL (Health in my Language)

Project information

Deliverables

Publications

Project information

Project information

Share this page

Download