en
Proceedings chapter
Open access
French

Statistical vs. Neural Machine Translation: A Comparison of MTH and DeepL at Swiss Post's Language Service

Presented at London (United-Kingdom), 15-16 November
Publication date2018
Abstract

This paper presents a study conducted in collaboration with Swiss Post's Language Service that aims to compare the performance of a generic neural machine translation system (DeepL) and a customised statistical machine translation system (Microsoft Translator Hub, MTH) in terms of post-editing effort and quality of the final translation for the language direction German-to-French. The results for automatic and human evaluations show that DeepL is overall better than MTH, but its quality is underestimated by the BLEU score.

Keywords
  • Machine translation
  • Neural machine translation
  • Statistical machine translation
  • Microsoft Translator Hub
  • DeepL
  • Evaluation
  • BLEU
  • Post-editing
  • Swiss Post
Citation (ISO format)
VOLKART, Lise, BOUILLON, Pierrette, GIRLETTI, Sabrina. Statistical vs. Neural Machine Translation: A Comparison of MTH and DeepL at Swiss Post’s Language Service. In: Proceedings of the 40th Conference Translating and the Computer. London (United-Kingdom). [s.l.] : [s.n.], 2018. p. 145–150.
Main files (1)
Proceedings chapter (Published version)
Identifiers
  • PID : unige:111777
ISBN978-2-9701095-5-6
2234views
938downloads

Technical informations

Creation11/28/2018 9:53:00 AM
First validation11/28/2018 9:53:00 AM
Update time03/15/2023 3:08:28 PM
Status update03/15/2023 3:08:28 PM
Last indexation02/12/2024 12:57:35 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack