Statistical Machine Translation

被引：0
作者：
Vatsa, Mukesh G. S. [1 ]
Joshi, Nikita [1 ]
Goswami, Sumit [2 ]
机构：
[1] DRDO, DESIDOC, Metcalfe House, Delhi 110054, India
[2] DRDO Bhavan, DRDO HQ, Delhi 110105, India
来源：
DESIDOC JOURNAL OF LIBRARY & INFORMATION TECHNOLOGY | 2010年 / 30卷 / 04期
关键词：
Statistical machine translation; machine learning; natural language processing; bilingual corpus;
D O I：
暂无
中图分类号：
G25 [图书馆学、图书馆事业]; G35 [情报学、情报工作];
学科分类号：
1205 ; 120501 ;
摘要：
Statistical Machine Translation (SMT) systems are based on bilingual sentence aligned data. The quality of translation depends on the data provided for translation learning. A huge parallel corpus is required for performing the statistical machine translation. The aim of this paper is to explore SMT using the Moses toolkit for creating a German-English translator. To perform the German to English translation, a parallel corpus of this language pair has been provided. Larger the size of the data provided for the training of the Moses decoder, more accurate is the translated output.
引用
收藏
页码：25 / 32
页数：8
相关论文
共 32 条
[1]  
Allauzen A., ERROR DETECTION CONF
[2]  
[Anonymous], 1996, EUR PARL P PAR CORP
[3]  
Babych B., 2003, 7 INT EAMT WORKSH MT
[4]  
Berger A.L., 1994, HLT 94 P WORKSH HUM, P157, DOI [10.3115/1075812.1075844, DOI 10.3115/1075812.1075844]
[5]  
Brown P. F., 1993, Computational Linguistics, V19, P263
[6]  
Carpuat M., 2007, P 2007 JOINT C EMPIR, V7, P61
[7]  
CHEN SF, 1993, P 31 ANN M ASS COMP, P9
[8]  
CHOMSKY N, 1956, IRE T INFORM THEOR, V2, P113
[9]  
Chomsky N., 1963, HDB MATH PSYCHOL, P323
[10]  
Chomsky N., 1958, INFORM CONTR, V1, P91, DOI DOI 10.1016/S0019-9958(58)90082-2
1234