Multi-source Transformer for Automatic Post-Editing of Machine Translation Output
Automatic post-editing (APE) of machine translation (MT) is the task of automatically fixing errors in a machine-translated text by learning from human corrections. Recent APE approaches have shown that best results are obtained by neural multi-source models that correct the raw MT output by also co...
Guardado en:
Autores principales: | Amirhossein Tebbifakhr, Matteo Negri, Marco Turchi |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Accademia University Press
2019
|
Materias: | |
Acceso en línea: | https://doaj.org/article/799e49c982374be099ce03ccbd4f40ce |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Multilingual Neural Machine Translation for Low-Resource Languages
por: Surafel M. Lakew, et al.
Publicado: (2018) -
Towards Automatic Subtitling: Assessing the Quality of Old and New Resources
por: Alina Karakanta, et al.
Publicado: (2020) -
Stylometry and Automatic Attribution of Medieval Liturgical Monodies
por: Francesco Unguendoli, et al.
Publicado: (2018) -
Deep Learning for Automatic Image Captioning in Poor Training Conditions
por: Caterina Masotti, et al.
Publicado: (2018) -
EVALITA Goes Social: Tasks, Data, and Community at the 2016 Edition
por: Pierpaolo Basile, et al.
Publicado: (2017)