DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages

Gabriele Sarti*, Arianna Bisazza, Ana Guerberof, Antonio Toral Ruiz

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

59 Downloads (Pure)

Abstract

We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. We find that post-editing is consistently faster than translation from scratch. However, the magnitude of productivity gains varies widely across systems and languages, highlighting major disparities in post-editing effectiveness for languages at different degrees of typological relatedness to English, even when controlling for system architecture and training data size. We publicly release the complete dataset including all collected behavioral data, to foster new research on the translation capabilities of NMT systems for typologically diverse languages.
Original languageEnglish
Title of host publicationProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
EditorsYoav Goldberg, Zornitsa Kozareva, Yue Zhang
Place of PublicationAbu Dhabi, United Arab Emirates
PublisherAssociation for Computational Linguistics (ACL)
Pages7795-7816
Number of pages22
DOIs
Publication statusPublished - Dec-2022
EventThe 2022 Conference on Empirical Methods in Natural Language Processing - Abu Dhabi National Exhibition Centre, Abu Dhabi, United Arab Emirates
Duration: 7-Dec-202211-Dec-2022
https://2022.emnlp.org/

Conference

ConferenceThe 2022 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP '22
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period07/12/202211/12/2022
Internet address

Keywords

  • resource
  • machine translation
  • post-editing
  • language typology
  • translation studies
  • deep learning

Fingerprint

Dive into the research topics of 'DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages'. Together they form a unique fingerprint.

Cite this