An experiment on Japanese-Uighur statistical machine translation with increased corpus

Author

Nimaiti, Maimitili ; Izumi, Yamamoto

Author_Institution

Nagoya Inst. of Technol., Nagoya, Japan

fYear

2014

fDate

18-20 Aug. 2014

Firstpage

490

Lastpage

495

Abstract

In this paper, we present the results of our work on the development of a phrase-based statistical machine translation system from Japanese to Uyghur - an agglutinative language with productive inflectional and derivational morphology. We experiment with different morpheme-level representations for Japanese-Uyghur parallel texts. We improve from our baseline 2.61 BLEU points for our phrase-based baseline model to 7.03 BLEU points for an improvement of 4.42 points.

Keywords

language translation; natural language processing; statistical analysis; text analysis; BLEU points; Japanese-Uighur statistical machine translation; Japanese-Uyghur parallel texts; agglutinative language; derivational morphology; morpheme-level representations; phrase-based baseline model; phrase-based statistical machine translation system; productive inflectional morphology; Computational modeling; Decoding; Morphology; Standards; Surface morphology; Syntactics; Training; Japanese; Phrase-Based approach; Statistical machine translation (SMT); Uyghur (Uighur);

fLanguage

English

Publisher

ieee

Conference_Titel

Cognitive Informatics & Cognitive Computing (ICCI*CC), 2014 IEEE 13th International Conference on

Conference_Location

London

Print_ISBN

978-1-4799-6080-4

Type

conf

DOI

10.1109/ICCI-CC.2014.6921504

Filename

6921504