: NLP Vocabulary: adaptive machine translation

applied NLP > machine translation > human-aided machine translation > adaptive machine translation

adaptive machine translation

Machine translation that includes user feedback to improve translation quality. In a post-editing scenario, user corrections of machine translation output are thus continuously incorporated into translation models, reducing or eliminating repetitive error editing. ( https://aclanthology.org/2021.ranlp-1.47/)

Adaptive Machine Translation purports to dynamically include user feedback to improve translation quality. (Etchegoyhen, Ponce, Gete & Ruiz, 2021)
Adaptive MT is a type of machine translation that utilizes feedback from users to improve the quality of the translations over time. (Moslem, Haque, Kelleher & Way, 2023)

Adaptive machine translation (MT) systems are a promising approach for improving the effectiveness of computer-aided translation (CAT) environments. (Simianer, Karimova & Riezler, 2016)
For adaptive MT with fuzzy matches it would be interesting to investigate dynamic few-shot example selection. (Moslem, Haque, Kelleher & Way, 2023)
Nevertheless adaptive MT with LLM few-shot incontext learning can surpass such quality especially for high-resource languages. (Moslem, Haque, Kelleher & Way, 2023)
This study examines the effectiveness of adaptive machine translation (AMT) for gender-neutral language (GNL) use in English-German translation using the ModernMT engine. (Kostikova, Daems & Lazarov, 2023)

http://data.loterre.fr/ark:/67375/8LP-LTWNJH3R-4

RDF/XML TURTLE JSON-LD Last modified 4/29/24

Loterre