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.
Zhenxin YANG
Chinese Academy of Sciences,University of Science and Technology of China
Miao LI
Chinese Academy of Sciences
Lei CHEN
Chinese Academy of Sciences
Kai SUN
University of Science and Technology of China
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Zhenxin YANG, Miao LI, Lei CHEN, Kai SUN, "A Morpheme-Based Weighting for Chinese-Mongolian Statistical Machine Translation" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 11, pp. 2843-2846, November 2016, doi: 10.1587/transinf.2016EDL8080.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8080/_p
Copy
@ARTICLE{e99-d_11_2843,
author={Zhenxin YANG, Miao LI, Lei CHEN, Kai SUN, },
journal={IEICE TRANSACTIONS on Information},
title={A Morpheme-Based Weighting for Chinese-Mongolian Statistical Machine Translation},
year={2016},
volume={E99-D},
number={11},
pages={2843-2846},
abstract={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.},
keywords={},
doi={10.1587/transinf.2016EDL8080},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - A Morpheme-Based Weighting for Chinese-Mongolian Statistical Machine Translation
T2 - IEICE TRANSACTIONS on Information
SP - 2843
EP - 2846
AU - Zhenxin YANG
AU - Miao LI
AU - Lei CHEN
AU - Kai SUN
PY - 2016
DO - 10.1587/transinf.2016EDL8080
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2016
AB - 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.
ER -