TREF - TRanslation Enhancement Framework for Japanese-English

Author

Wloka, Bartholomaäus ; Winiwarter, Werner

Author_Institution

Dept. of Sci. Comput., Univ. of Vienna, Vienna, Austria

fYear

2010

fDate

18-20 Oct. 2010

Firstpage

541

Lastpage

546

Abstract

We present a method for improving existing statistical machine translation methods using an knowledge-base compiled from a bilingual corpus as well as sequence alignment and pattern matching techniques from the area of machine learning and bioinformatics. An alignment algorithm identifies similar sentences, which are then used to construct a better word order for the translation. Our preliminary test results indicate a significant improvement of the translation quality.

Keywords

bioinformatics; knowledge based systems; language translation; learning (artificial intelligence); natural language processing; word processing; Japanese English translation; TREF; bilingual corpus; bioinformatics; machine learning; pattern matching techniques; sequence alignment; statistical machine translation method; translation enhancement framework; Artificial neural networks; Atmospheric measurements; Bioinformatics; Databases; Pollution measurement; Semantics; Tagging; Machine Translation; Sequence Alignment; Syntactical Analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Information Technology (IMCSIT), Proceedings of the 2010 International Multiconference on

Conference_Location

Wisla

ISSN

2157-5525

Print_ISBN

978-1-4244-6432-6

Type

conf

DOI

10.1109/IMCSIT.2010.5679926

Filename

5679926