International Journal of Information and Communication Technology Research
مجله بین المللی ارتباطات و فناوری اطلاعات
International Journal of Information and Communication Technology Research
Engineering & Technology
http://ijict.itrc.ac.ir
1
admin
2251-6107
2783-4425
doi
1652
25391
en
jalali
1391
12
1
gregorian
2013
3
1
5
1
online
1
fulltext
fa
Statistical Machine Translation (SMT) for Highly-Inflectional Scarce-Resource Language
فناوری اطلاعات
Information Technology
پژوهشي
Research
<p>Statistical Machine Translation (SMT) is a machine translation paradigm, in which translations are generated on the base of statistical models. In this system, parameters are derived from an analysis of a parallel corpus, and SMT quality depends on the ability of learning word translations. Enriching the SMT by a suitable morphology analyser decreases out of vocabulary words and dictionary size dramatically. This could be more considerable when it deals with a highly-inflectional, low-resource, language like Persian. Defining a suitable granularity for word segment may improve the alignment quality in the parallel corpus. In this paper different schemes and word’s combinations segments in a SMT’s experiment from Persian to English language are prospected and the best one-to-one alignment, which is called En-like scheme, is proposed. By using the mentioned scheme the translation’s quality from Persian to English is improved about 3 points with respect to BLEU measure over the phrase-based SMT.</p>
Statistical Machine Translation, Segmentation Schemes, Lexical Granularities, Morpheme, Persian Language
39
52
http://ijict.itrc.ac.ir/browse.php?a_code=A-10-27-138&slc_lang=fa&sid=1
Saman
Namdar
1003194753284600468
1003194753284600468
Yes
Hesham
Faili
1003194753284600469
1003194753284600469
No
Shahram
Khadivi
1003194753284600470
1003194753284600470
No