Conference Proceedings

Findings of the WMT 2019 biomedical translation shared task: Evaluation for MEDLINE abstracts and biomedical terminologies

R Bawden, KB Cohen, C Grozea, AJ Yepes, M Kittner, M Krallinger, N Mah, A Névéol, M Neves, F Soares, A Siu, K Verspoor, MV Navarro

Wmt 2019 4th Conference on Machine Translation Proceedings of the Conference | ASSOC COMPUTATIONAL LINGUISTICS-ACL | Published : 2019

Abstract

In the fourth edition of the WMT Biomedical Translation task, we considered a total of six languages, namely Chinese (zh), English (en), French (fr), German (de), Portuguese (pt), and Spanish (es). We performed an evaluation of automatic translations for a total of 10 language directions, namely, zh/en, en/zh, fr/en, en/fr, de/en, en/de, pt/en, en/pt, es/en, and en/es. We provided training data based on MEDLINE abstracts for eight of the 10 language pairs and test sets for all of them. In addition to that, we offered a new sub-task for the translation of terms in biomedical terminologies for the en/es language direction. Higher BLEU scores (close to 0.5) were obtained for the es/en, en/es an..

View full abstract

University of Melbourne Researchers

Grants

Funding Acknowledgements

We would like to thank all participants in the challenges, and especially those who supported us for the manual evaluation, including Melana Uceda (es/en). We also would like to thank the participants Aihu Zhang (team OOM), Antoni Oliver Gonzalez (team MT-UOC-UPF), Fabien Cromi`eres (team KU), Sadaf Abdul-Rauf (team NRPU) and Stefania Duma (team UHH-DS) for providing summaries about their systems, which we included in the manuscript. MK and FS acknowledge support from the encargo de gestion SEAD-BSC-CNS of Plan for the Advancement of Language Technology (Plan TL) and the Interreg Sudoe ICTUSnet project.