Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Automatic post-editing"'
Publikováno v:
IEEE Access, Vol 10, Pp 117053-117066 (2022)
Nowadays Automatic Speech Recognition (ASR) systems can accurately recognize which words are said. However, due to the disfluency, grammatical error, and other phenomena in spontaneous speech, the verbatim transcription of ASR impairs its readability
Externí odkaz:
https://doaj.org/article/a36a71c126324d67b8ebfe466add04aa
Publikováno v:
IEEE Access, Vol 10, Pp 67047-67057 (2022)
Automatic post-editing (APE) research aims to investigate methods for correcting systematic errors in machine translation (MT) results. Recent work has shown successful practices of APE for improving MT output quality; however, their effectiveness st
Externí odkaz:
https://doaj.org/article/d3aa976647d244318ee09e7d62e1c12c
Publikováno v:
IEEE Access, Vol 10, Pp 21032-21040 (2022)
Automatic post-editing (APE) research considers methods for correcting translation results inferred by machine translation systems. The training of APE models, generally require triplets including a source sentence ( $src$ ), machine translation sent
Externí odkaz:
https://doaj.org/article/7dd0cb7295504b99a386d76135ac49e8
Publikováno v:
IEEE Access, Vol 10, Pp 28274-28282 (2022)
Synthetic training data has been extensively used to train Automatic Post-Editing (APE) models in many recent studies because the quantity of human-created data has been considered insufficient. However, the most widely used synthetic APE dataset, eS
Externí odkaz:
https://doaj.org/article/4109634095304fde9b189dcebf10de82
Publikováno v:
IEEE Access, Vol 9, Pp 123754-123763 (2021)
Automatic post editing (APE) researches aim to correct errors in the machine translation results. Recently, APE research has mainly been conducted in two directions: noise-based APE and adapter-based APE. This study poses three questions based on exi
Externí odkaz:
https://doaj.org/article/e6f19f7523014d83bf9bd10b82a1ce08
Kniha
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Despite the latest improvements on machine translation, professional translators still must review and post-edit the automatic output to ensure high-quality translations. The research on automating this process lacks an interactive post-editing envir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be96114115b59152daca2e18e138302d
Autor:
Murhaf Hossari, Dimitar Shterionov, Eric Paquin, Joachim Wagner, Andy Way, Félix do Carmo, Dag Schmidtke, Joss Moorkens, Declan Groves
Publikováno v:
Machine Translation
This article presents a review of the evolution of automatic post-editing, a term that describes methods to improve the output of machine translation systems, based on knowledge extracted from datasets that include post-edited content. The article de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f5007d5d5308d1d1d3d4ac459002b25
https://doi.org/10.1007/s10590-020-09252-y
https://doi.org/10.1007/s10590-020-09252-y
Autor:
MAY MYO ZIN
Supervisor:Nguyen Minh Le
先端科学技術研究科
博士
先端科学技術研究科
博士
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=jairo_______::f24d8847f494f3ccd91e5f565d11fb69
http://hdl.handle.net/10119/18138
http://hdl.handle.net/10119/18138
Publikováno v:
IEEE Access, Vol 9, Pp 123754-123763 (2021)
Automatic post editing (APE) researches aim to correct errors in the machine translation results. Recently, APE research has mainly been conducted in two directions: noise-based APE and adapter-based APE. This study poses three questions based on exi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3759d7952230c9e9bdbaa5ffa05c26a
https://ieeexplore.ieee.org/document/9528385/
https://ieeexplore.ieee.org/document/9528385/