no code implementations • NAACL 2021 • Yu Sun, Shaolin Zhu, Feng Yifan, Chenggang Mi
In this paper, we propose an approach based on transfer learning to mine parallel sentences in the unsupervised setting. With the help of bilingual corpora of rich-resource language pairs, we can mine parallel sentences without bilingual supervision of low-resource language pairs.
no code implementations • COLING 2018 • Chenggang Mi, Yating Yang, Lei Wang, Xi Zhou, Tonghai Jiang
Neural machine translation models integrating results of loanword identification experiments achieve the best results on OOV translation(with 0. 5-0. 9 BLEU improvements)
no code implementations • RANLP 2017 • Chenggang Mi, Yating Yang, Rui Dong, Xi Zhou, Lei Wang, Xiao Li, Tonghai Jiang
To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach.