Differences between SMT and NMT Output - a Translators' Point of View

In this study, we compare the output quality of two MT systems, a statistical (SMT) and a neural (NMT) engine, customised for Swiss Post's Language Service using the same training data. We focus on the point of view of professional translators and investigate how they perceive the differences between the MT output and a human reference (namely deletions, substitutions, insertions and word order). Our findings show that translators more frequently consider these differences to be errors in SMT than NMT, and that deletions are the most serious errors in both architectures. We also observe there to be less agreement on differences to be corrected in NMT than SMT, suggesting that errors are easier to identify in SMT. These findings confirm the ability of NMT to produce correct paraphrases, which could also explain why BLEU is often considered to be an inadequate metric to evaluate the performance of NMT systems