2024-03-29T05:13:50Z
https://meral.edu.mm/oai
oai:meral.edu.mm:recid/4969
2021-12-13T04:05:49Z
1582963302567:1597824273898
user-ucsy
Implementation of Word Alignment System for English- Myanmar Machine Translation
Khaing, Ei Ei
Soe, Khin Mar
Statistical word alignment models have beenwidely used for various Natural LanguageProcessing (NLP) problem. In statistical machinetranslation, word alignment models are trained onbilingual corpora. To build an SMT system werequire bitext and a word alignment of that bitext, aswell as language models built from target languagedata. A word alignment for a parallel sentence pairrepresents the correspondence between words in asource language and their translations in a targetlanguage. This system will use the IBM model whichis based on the EM algorithm. This system deals withthe step of word alignment. In this paper, C#implementation of a word alignment algorithm isused to testing the source and target sentences. Thissystem also uses a English-Myanmar dictionary tobootstrap the Expectation Maximization (EM)algorithm.
2010-12-16
http://hdl.handle.net/20.500.12678/0000004969
https://meral.edu.mm/records/4969