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

Jonathan Mutal, Lise Volkart, Pierrette Bouillon, Sabrina Girletti, Paula Estrella


Abstract
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 lower agreement on differences to be corrected in NMT than in 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 as an inadequate metric to evaluate the performance of NMT systems.
Anthology ID:
W19-8709
Volume:
Proceedings of the Human-Informed Translation and Interpreting Technology Workshop (HiT-IT 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Venues:
RANLP | WS
SIG:
Publisher:
Incoma Ltd., Shoumen, Bulgaria
Note:
Pages:
75–81
Language:
URL:
https://aclanthology.org/W19-8709
DOI:
10.26615/issn.2683-0078.2019_009
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/W19-8709.pdf