This paper describes the methodology followed to build a neural machine translation system in the biomedical domain for the English-Catalan language pair. This task can be considered a low-resourced task from the point of view of the domain and the language pair. To face this task, this paper reports experiments on a cascade pivot strategy through Spanish for the neural machine translation using the English-Spanish SCIELO and Spanish-Catalan El Peri´odico database. To test the final performance of the system, we have created a new test data set for English-Catalan in the biomedical domain which is freely available on request.
@InProceedings{COSTA-JUSSÀ18.3, author = {Marta R. Costa-jussà ,Noe Casas and Maite Melero}, title = {English-Catalan Neural Machine Translation in the Biomedical Domain}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {may}, date = {7-12}, location = {Miyazaki, Japan}, editor = {Maite Melero and Martin Krallinger and
Aitor Gonzalez-Agirre}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-03-0}, language = {english} }
Summary of the paper