Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Findings of the WMT 2017 biomedical translation shared task

: Jimeno Yepes, Antonio; Névéol, Aurélie; Neves, Mariana; Verspoor, Karin; Bojar, Ondrej; Boyer, Arthur; Grozea, Cristian; Haddow, Barry; Kittner, Madeleine; Lichtblau, Yvonne; Pecina, Pavel; Roller, Roland; Rosa, Rudolf; Siu, Amy; Thomas, Philippe; Trescher, Saskia

Volltext (PDF; )

Association for Computational Linguistics -ACL-:
Second Conference on Machine Translation, WMT 2017. Proceedings : September 7-8, 2017 Copenhagen, Denmark
Stroudsburg/Pa.: ACL, 2017
ISBN: 978-1-945626-96-8
Conference on Machine Translation (WMT) <2, 2017, Copenhagen>
Conference on Empirical Methods in Natural Language Processing (EMNLP) <2017, Copenhagen>
European Commission EC
H2020; 644402; HimL
European Commission EC
H2020; 644753; KConnect
Konferenzbeitrag, Elektronische Publikation
Fraunhofer FOKUS ()

Automatic translation of documents is an important task in many domains, including the biological and clinical domains. The second edition of the Biomedical Translation task in the Conference of Machine Translation focused on the automatic translation of biomedical-related documents between English and various European languages. This year, we addressed ten languages: Czech, German, English, French, Hungarian, Polish, Portuguese, Spanish, Romanian and Swedish. Test sets included both scientific publications (from the Scielo and EDP Sciences databases) and health-related news (from the Cochrane and UK National Health Service web sites). Seven teams participated in the task, submitting a total of 82 runs. Herein we describe the test sets, participating systems and results of both the automatic and manual evaluation of the translations.