Activiteiten per jaar
Samenvatting
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.
Originele taal-2 | English |
---|---|
Titel | Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing |
Redacteuren | Yoav Goldberg, Zornitsa Kozareva, Yue Zhang |
Plaats van productie | Abu Dhabi, United Arab Emirates |
Uitgeverij | Association for Computational Linguistics (ACL) |
Pagina's | 7795-7816 |
Aantal pagina's | 22 |
DOI's | |
Status | Published - dec.-2022 |
Evenement | The 2022 Conference on Empirical Methods in Natural Language Processing - Abu Dhabi National Exhibition Centre, Abu Dhabi, United Arab Emirates Duur: 7-dec.-2022 → 11-dec.-2022 https://2022.emnlp.org/ |
Conference
Conference | The 2022 Conference on Empirical Methods in Natural Language Processing |
---|---|
Verkorte titel | EMNLP '22 |
Land/Regio | United Arab Emirates |
Stad | Abu Dhabi |
Periode | 07/12/2022 → 11/12/2022 |
Internet adres |
Activiteiten
- 1 Professional or public presentation
-
Towards User-centric Interpretability of NLP Models
Gabriele Sarti (Speaker)
18-mei-2022Activiteit: Professional or public presentation › Professional
Datasets
-
DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages
Sarti, G. (Owner), Bisazza, A. (Owner), Guerberof Arenas, A. (Owner) & Toral Ruiz, A. (Owner), University of Groningen, mei-2022
https://github.com/gsarti/divemt en nog één link, https://huggingface.co/datasets/GroNLP/divemt (minder tonen)
Dataset