Title : ( IBM word-alignment model I for statistical machine translation )
Authors: neda daneshgar , Majid Sarmad ,
Full TextAbstract
This paper describes the word alignment based on IBM model 1 for an English-Persian Parallel Corpus (Mizan). We only consider 100,000 sentence pairs. It is been obtained that for each sentence, more than 80 percentage of word alignments between English and Persian words are reasonable.
Keywords
, word alignment, statistical models, IBM model 1, EM algorithm
@inproceedings{paperid:1046100,
author = {Daneshgar, Neda and Sarmad, Majid},
title = {IBM word-alignment model I for statistical machine translation},
booktitle = {چهل و پنجمین کنفرانس ریاضی ایران},
year = {2014},
location = {سمنان, IRAN},
keywords = {word alignment; statistical models; IBM model 1; EM algorithm},
}
%0 Conference Proceedings
%T IBM word-alignment model I for statistical machine translation
%A Daneshgar, Neda
%A Sarmad, Majid
%J چهل و پنجمین کنفرانس ریاضی ایران
%D 2014
