Statistical Machine Translation (SMT) for Highly-Inflectional Scarce-Resource Language
عنوان مقاله: Statistical Machine Translation (SMT) for Highly-Inflectional Scarce-Resource Language
شناسه ملی مقاله: JR_ITRC-5-1_005
منتشر شده در در سال 1391
شناسه ملی مقاله: JR_ITRC-5-1_005
منتشر شده در در سال 1391
مشخصات نویسندگان مقاله:
Saman Namdar
Hesham Faili
Shahram Khadivi
خلاصه مقاله:
Saman Namdar
Hesham Faili
Shahram Khadivi
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 ۳ points with respect to BLEU measure over the phrase-based SMT.
کلمات کلیدی: Statistical Machine Translation, Segmentation Schemes, Lexical Granularities, Morpheme, Persian Language
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/1425805/