Creating an SMT engine for pharmaceutical and medical texts in the Romanian-Spanish language pair

  • Adrià Martín Universitat Autònoma de Barcelona (Catalunya)
  • Víctor Peña-Irles Universitat Autònoma de Barcelona (Catalunya)

Abstract

This article describes the process of creation of a statistical machine translation engine specialised in medicine for the Romanian--Spanish language pair. The engine was based on free corpora available in internet. The article describes the use of the platform MTradumàtica developed in the context of a research project by the Tradumàtica research group, aimed at promoting the use of MT among translators. The article can be interpreted as the evidence that the aim of promoting MT among translators has been attained in this particular case, and it suggests that the profile of the translators is valid to carry out processes of customisation of MT engines.

Author Biography

Adrià Martín, Universitat Autònoma de Barcelona (Catalunya)

Adrià Martín-Mor is a professor at the Departament de Traducció i d’Interpretació i d’Estudis de l’Àsia Oriental (Universitat Autònoma de Barcelona, Catalonia) and at the Dipartimento di Filologia, Letteratura e Linguistica (Universidade de Casteddu, Sardinia). He is a member of the Tradumàtica research group at UAB, where he coordinates training programmes in translation technologies such as the Tradumàtica MA and the Tradumàtica Summer School. He holds an MA and a PhD on Translation Studies and his research interests are the automation of the translation process (Computer-Assisted Translation, Machine Translation), minoritised languages and free software for translation.

Published
2017-12-31
How to Cite
Martín, A., & Peña-Irles, V. (2017). Creating an SMT engine for pharmaceutical and medical texts in the Romanian-Spanish language pair. Linguamática, 9(2), 45-53. https://doi.org/10.21814/lm.9.2.254
Section
Research Articles