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...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Jinyi Zhang, Tadahiro Matsumoto
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2019-05-01
coleção:	Applied Sciences
Assuntos:	back translation Chinese-Japanese translation corpus augmentation decoder encoder Japanese-Chinese translation LSTM neural machine translation sentence segmentation
Acesso em linha:	https://www.mdpi.com/2076-3417/9/10/2036
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!