Injected linguistic tags to improve phrase based SMT

Author

Oransa, Waleed ; Kouta, Mohamed ; Sakre, Mohammed

Author_Institution

Coll. of Comput. & Inf. Technol., Arab Acad. for Sci. & Technol., Cairo, Egypt

Volume

4

fYear

2010

fDate

26-28 Feb. 2010

Firstpage

329

Lastpage

333

Abstract

This paper presents Injected Tags (ITs) approach, that improves the phrase based statistical machine translation (PBSMT) approach. This Injected Tags approach has been applied to Â¿English into Arabic translationÂ¿. This approach is language independent and can be used with any language pair. It has shown considerable improvement of the translation quality of at least 13% increase of BLEU score. The approach has been evaluated and has been compared with several online Machine Translation (MT) services. The experiments reveal that the results achieved by this approach considered significant enhancements over PBSMT.

Keywords

language translation; natural language processing; statistical analysis; English-Arabic translation; injected linguistic tags; machine translation service; phrase based statistical machine translation; Educational institutions; Employment; Information systems; Information technology; Interpolation; Morphology; Natural languages; Scalability; Surface-mount technology; Tagging; PBSMT; Phrase Based Machine Translation; SMT Approach; Statistical Machine Translation;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on

Conference_Location

Singapore

Print_ISBN

978-1-4244-5585-0

Electronic_ISBN

978-1-4244-5586-7

Type

conf

DOI

10.1109/ICCAE.2010.5451681

Filename

5451681