CH-EN Syntran (CES)1.0 | {including n2p conversion (java)}
a miniature*, rule-based machine translation tool for Chinese-to-English translation
Shuo Zhang | Machine Translation (advisor:Dr George Wilson)
attached files:
- CH-ENSyntran.zip (contains all the files needed for the translation engine, including the preprocessor CharacterCoversion InputExp.jar properly configured, inputfile.txt which the Chinese sentence is stored, grammar, lexicon, transfer rules files, ST_Config.txt, and the shell script for connecting the preprocessor, as well as SyntacticTransfer.pl and pcpatr)
- InputExp.jar(n2p conversion, a java tool written by me using pinyin4j library, preprocessor that performs Character-to-pinyin conversion, may be invoked alone)
- SZ_grm6.txt (grammar file)
- SZ_Lex5.txt (lexicon file)
- C2E_TR.txt (transfer rules file)
- InputExp.java (main class) | ReadFile.java (java source code for the two classes in the InputExp.jar) | javadoc (for InputExp.class)
- Demo file with sample sentence translations, also available for view at the end of this document (to see Chinese characters properly please make sure you have correct encodings in your browser)
- *the term 'miniature' applies because the current lexicon and grammar is small. This is more of a demo of the method and tool at this stage.