Corpus Augmentation for Neural Machine Translation with Chinese-Japanese Parallel Corpora

Corpus Augmentation for Neural Machine Translation with Chinese-Japanese Parallel Corpora

The translation quality of Neural Machine Translation (NMT) systems depends strongly on the training data size. Sufficient amounts of parallel data are, however, not available for many language pairs. This paper presents a corpus augmentation method, which has two variations: one is for all language...

Descripción completa

Detalles Bibliográficos
Autores principales: Jinyi Zhang, Tadahiro Matsumoto
Formato: Artículo
Lenguaje:English
Publicado: MDPI AG 2019-05-01
Colección:Applied Sciences
Materias:
back translation
Chinese-Japanese translation
corpus augmentation
decoder
encoder
Japanese-Chinese translation
LSTM
neural machine translation
sentence segmentation
Acceso en línea:https://www.mdpi.com/2076-3417/9/10/2036

Internet

https://www.mdpi.com/2076-3417/9/10/2036

Ejemplares similares