archive_header_en_20260623154835960.png

Change account information such as the email address and password on the account setting screen common to Confit.

Login required to view

Password required to view

Presentation Information

Session Details

To browse or post comments, you must log in.

You cannot post comments as it is outside the comment posting period.

This comment has been deleted. You cannot reply to this comment.

Program Type

Application of Unsupervised NMT Technique to Japanese--Chinese Machine Translation

Neural machine translation (NMT) often suffers in low-resource scenarios where sufficiently large-scale parallel corpora cannot be obtained. Therefore, a recent line of unsupervised NMT models based on monolingual corpus is emerging. In this work, we perform three sets of experiments that analyze the application of unsupervised NMT model in Japanese--Chinese machine translation. We report 30.13 BLEU points for ZH--JA and 23.42 BLEU points for JA--ZH.

The Japanese Society for Artificial Intelligence

JSAI2019

JSAI2019

[3B4-E-2-04]Application of Unsupervised NMT Technique to Japanese--Chinese Machine Translation

Keywords: