A Morpheme-Based Weighting for Chinese-Mongolian Statistical Machine Translation

Zhenxin YANG  Miao LI  Lei CHEN  Kai SUN  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.11   pp.2843-2846
Publication Date: 2016/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDL8080
Type of Manuscript: LETTER
Category: Natural Language Processing
Keyword: 
machine translation,  morpheme-based weighting,  multiple decoding paths,  low-resource language,  

Full Text: PDF>>
Buy this Article




Summary: 
In this paper, a morpheme-based weighting and its integration method are proposed as a smoothing method to alleviate the data sparseness in Chinese-Mongolian statistical machine translation (SMT). Besides, we present source-side reordering as the pre-processing model to verify the extensibility of our method. Experi-mental results show that the morpheme-based weighting can substantially improve the translation quality.