Zobrazeno 1 - 10
of 505
pro vyhledávání: '"Automatic post-editing"'
This exploratory study investigates the potential of multilingual Automatic Post-Editing (APE) systems to enhance the quality of machine translations for low-resource Indo-Aryan languages. Focusing on two closely related language pairs, English-Marat
Externí odkaz:
http://arxiv.org/abs/2410.17973
Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment, providing both scores and fine-grained feedback. Although approaches such as GEMBA-MQM have shown state-of-the-art performance on
Externí odkaz:
http://arxiv.org/abs/2409.14335
Autor:
Zhang, Xu, Wan, Xiaojun
Automatic post-editing (APE) aims to reduce manual post-editing efforts by automatically correcting errors in machine-translated output. Due to the limited amount of human-annotated training data, data scarcity is one of the main challenges faced by
Externí odkaz:
http://arxiv.org/abs/2209.07759
Autor:
do Carmo, Félix, Shterionov, Dimitar, Moorkens, Joss, Wagner, Joachim, Hossari, Murhaf, Paquin, Eric, Schmidtke, Dag, Groves, Declan, Way, Andy
Publikováno v:
Machine Translation, 2021 Jun 01. 35(2), 101-143.
Externí odkaz:
https://www.jstor.org/stable/48758491
Semi-supervised learning that leverages synthetic data for training has been widely adopted for developing automatic post-editing (APE) models due to the lack of training data. With this aim, we focus on data-synthesis methods to create high-quality
Externí odkaz:
http://arxiv.org/abs/2204.03896
This paper describes Netmarble's submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. First, we propose a Curriculum Training Strategy in training stages. Facebook Fair's WMT19 news translation model was
Externí odkaz:
http://arxiv.org/abs/2109.06515
Data building for automatic post-editing (APE) requires extensive and expert-level human effort, as it contains an elaborate process that involves identifying errors in sentences and providing suitable revisions. Hence, we develop a self-supervised d
Externí odkaz:
http://arxiv.org/abs/2111.12284
Autor:
Shterionov, Dimitar, do Carmo, Félix, Moorkens, Joss, Hossari, Murhaf, Wagner, Joachim, Paquin, Eric, Schmidtke, Dag, Groves, Declan, Way, Andy
Publikováno v:
Machine Translation, 2020 Sep 01. 34(2/3), 67-96.
Externí odkaz:
https://www.jstor.org/stable/48740616
Kniha
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.