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

Yuting Zhao

Presentation information

International Session

International Session » [ES] E-2 Machine learning

[3B4-E-2] Machine learning: social links

Thu. Jun 6, 2019 3:50 PM - 5:30 PM Room B (2F Main hall B)

Chair: Lieu-Hen Chen (National Chi Nan University), Reviewer: Yasufumi Takama (Tokyo Metropolitan University)

4:50 PM - 5:10 PM

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

〇Yuting Zhao¹, Longtu Zhang¹, Mamoru Komachi¹ (1. Tokyo Metropolitan University)

Keywords:NLP

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.