Findings of the WMT 2017 Biomedical Translation Shared Task

Proceedings of the Conference on Machine Translation (WMT), Volume 2: Shared Task Papers, pages 234–247 Copenhagen, Denmark, September 711, 2017. c⃝2017 Association for Computational Linguistics Findings of the WMT 2017 Biomedical Translation Shared Task Antonio Jimeno Yepes IBM Research Australia Aur´elie N´ev´eol LIMSI, CNRS, Uni. Paris Saclay, France Mariana Neves HPI Uni. Potsdam, BfR, Germany Karin Verspoor Uni. Melbourne, Australia Ondˇrej Bojar Charles Uni., Czech Rep. Arthur Boyer LIMSI, CNRS, Uni. Paris Saclay, France Cristian Grozea Fraunhofer Institute, Germany Barry Haddow Uni. Edinburgh, UK Madeleine Kittner Humboldt Uni., Germany Yvonne Lichtblau Humboldt Uni., Germany Pavel Pecina Charles Uni., Czech Rep. Roland Roller DFKI, Germany Rudolf Rosa Charles Uni., Czech Rep. Amy Siu MPI f¨ur Informatik, Germany Philippe Thomas DFKI, Germany Saskia Trescher Humboldt Uni., Germany Abstract Automatic translation of documents is an important task in many domains, in- cluding the biological and clinical do- mains. The second edition of the Biomed- ical Translation task in the Conference of Machine Translation focused on the au- tomatic translation of biomedical-related documents between English and various European languages. This year, we ad- dressed ten languages: Czech, German, English, French, Hungarian, Polish, Por- tuguese, Spanish, Romanian and Swedish. Test sets included both scientific publica- tions (from the Scielo and EDP Sciences databases) and health-related news (from the Cochrane and UK National Health Ser- vice web sites). Seven teams participated in the task, submitting a total of 82 runs. Herein we describe the test sets, participat- ing systems and results of both the auto- matic and manual evaluation of the trans- lations. 1 Introduction Automatic translation of texts allows readers to gain access to information present in documents written in a language in which the reader is not fluent. We identify two main use cases of ma- chine translation (MT) in the biomedical domain: (a) making health information available to health professionals and the general public in their own language; and (b) assisting health professionals and researchers in writing reports of their research in English. In addition, it creates an opportu- nity for natural language processing (NLP) tools to be applied to domain-specific texts in languages for which few domain-relevant tools are available; i.e., the texts can be translated into a language for which there are more resources. The second edition of the Biomedical Transla- tion Task in the Conference for Machine Trans- lation (WMT)1 builds on the first edition (Bo- jar et al., 2016) by offering seven additional lan- guage pairs and new test sets. This year, we ex- panded to a total of ten languages in the biomed- ical task, namely, Czech (cs), German (de), En- glish (en), French (fr), Hungarian (hu), Polish (pl), Portuguese (pt), Spanish (es), Romanian (ro) and Swedish (sv). Test sets included scientific publica- tions from the Scielo and EDP Sciences databases and health-related news from Cochrane and the UK National Health Service (NHS). Participants were challenged to build systems to enable translation from English to all other lan- 1http://www.statmt.org/wmt17/ biomedical-translation-task.html 234 guages, as well as from French, Spanish …

Content truncated to 500 words