Title :
TREF - TRanslation Enhancement Framework for Japanese-English
Author :
Wloka, Bartholomaäus ; Winiwarter, Werner
Author_Institution :
Dept. of Sci. Comput., Univ. of Vienna, Vienna, Austria
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;
Conference_Titel :
Computer Science and Information Technology (IMCSIT), Proceedings of the 2010 International Multiconference on
Conference_Location :
Wisla
Print_ISBN :
978-1-4244-6432-6
DOI :
10.1109/IMCSIT.2010.5679926
