Comparison of SYSTRAN and Google Translate for English→Portuguese

Authors

  • Rodrigo Gomes de Oliveira University of Bremen
  • Dimitra Anastasiou SFB/TR8 Spatial Cognition Computer Science & Languages and Literary Studies University of Bremen, Germany

Abstract

Two machine translation (MT) systems, a statistical MT (SMT) system and a hybrid system (rule-based and SMT) were tested in order to compare various MT performances. The source language was English (EN) and the target language Portuguese (PT). The SMT tool gave much fewer errors than the hybrid system. Major problem areas of both systems concerned the transfer of verb systems from source to target language, and of the hybrid system the word-to-word translation, since its resources are mainly dictionaries and not corpora.

 

 

Keywords

statistical machine translation, rule-based machine translation, SYSTRAN, Google Translate

DOI

https://doi.org/10.5565/rev/tradumatica.14

Published

2011-12-12

Downloads

Copyright (c) 2011 Rodrigo Gomes de Oliveira, Dimitra Anastasiou

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.