Neural Machine Translation (NMT) has attracted increasing attention in the recent years. However, it tends to require very large training corpora which could prove problematic for languages with low resources. For this reason, Statistical Machine Translation (SMT) continues to be a popular approach for low-resource language pairs. In this work, we address English-Basque translation and compare the performance of three contemporary statistical and neural machine translation systems: OpenNMT, Moses SMT and Google Translate. For evaluation, we employ an open-domain and an IT-domain corpora from the WMT16 resources for machine translation. In addition, we release a small dataset (Berriak) of 500 highly-accurate English-Basque translations of complex sentences useful for a thorough testing of the translation systems.
@InProceedings{JAUREGI UNANUE18.101, author = {Inigo Jauregi Unanue and Lierni Garmendia Arratibel and Ehsan Zare Borzeshi and Massimo Piccardi}, title = "{English-Basque Statistical and Neural Machine Translation}", booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {May 7-12, 2018}, address = {Miyazaki, Japan}, editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European Language Resources Association (ELRA)}, isbn = {979-10-95546-00-9}, language = {english} }
Summary of the paper