Myanmar-English Machine Translation Model

被引:0
作者
Nwet, Khin Thandar [1 ]
Soe, Khin Mar [1 ]
机构
[1] Univ Comp Studies, Nat Language Proc Lab, Yangon, Myanmar
来源
GENETIC AND EVOLUTIONARY COMPUTING | 2017年 / 536卷
关键词
Asian languages; Parallel corpus; Treebank; Machine translation;
D O I
10.1007/978-3-319-48490-7_23
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Natural Language Processing (NLP) is the field that strives to fill the communication gap between the different sections of societies One of the NLP processes, Machine Translation (MT) is used to translate any language from native language by understanding and generating natural language. The research in Myanmar-English MT has started since 2010. However, the translation accuracy is not becoming raise since the complex syntactic structure of Myanmar Language and the scarceness of resources. We found that it takes a lot of time to collect language resources such as Myanmar-English aligned corpora and Treebank. This paper presents current work of Myanmar-English machine translation system based on statistical methods. The aim of this paper is to introduce the Myanmar-English translation model and the comparative study using Asian Language Tree-bank (ALT) data.
引用
收藏
页码:195 / 203
页数:9
相关论文
共 20 条
  • [1] [Anonymous], 2002, TECHNICAL REPORT
  • [2] [Anonymous], 1999, GRID BLUEPRINT NEW C
  • [3] Aung N.T.T., 2011, INT J COMPUT APPL, V27
  • [4] Czajkowski K, 2001, 10TH IEEE INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE DISTRIBUTED COMPUTING, PROCEEDINGS, P181, DOI 10.1109/HPDC.2001.945188
  • [5] Htay H. H., 2008, 6 WORKSH AS LANG RES
  • [6] Kikui Genichiro., 2003, P EUROSPEECH, P381
  • [7] May P, 2006, LECT NOTES COMPUT SC, V4128, P1148
  • [8] Myint P.H., 2011, P 2011 INT C INF COM
  • [9] Nwet K.T., 2011, SICE ANN C 13 18 SEP
  • [10] Nwet K.T., 2016, DEV WORD PHRASE ALIG