Statistical Model of Length Based Methods in Developing English-Myanmar Parallel Corpus

dc.contributor.author	Han, Kyi Kyi
dc.contributor.author	Htay, Hla Hla
dc.date.accessioned	2019-08-01T14:46:01Z
dc.date.available	2019-08-01T14:46:01Z
dc.date.issued	2009-12-30
dc.identifier.uri	http://onlineresource.ucsy.edu.mm/handle/123456789/1591
dc.description.abstract	The paper is about developing an aligned English-Myanmar parallel corpus. This paper will describe method for aligning sentences based on simple statistical model of length. Parallel corpus is pairs of translation alignment of the bitext. We have used Gale & Church method to get translation alignments. Parallel corpus helps in making statistical bilingual dictionary, in supporting statistical machine translation and in supporting in training data for word sense disambiguation. The program is implemented in Java language.	en_US
dc.language.iso	en	en_US
dc.publisher	Fourth Local Conference on Parallel and Soft Computing	en_US
dc.subject	character	en_US
dc.subject	parallel corpus	en_US
dc.subject	translation	en_US
dc.subject	word	en_US
dc.title	Statistical Model of Length Based Methods in Developing English-Myanmar Parallel Corpus	en_US
dc.type	Article	en_US