This is the Open Source and UIMA-based application drawn out from the European project TTC Terminology Extraction, Translation Tools and Comparable Corpora. This project aims at leveraging machine translation, computer-assisted translation and multilingual content management tools by automatically generating bilingual terminologies from comparable corpora in five European languages (English, French, German, Spanish and one under-resourced language, Latvian), as well as in Chinese and Russian.

This application extracts monolingual terminologies and generates bilingual dictionaries from these terminologies by the means of distributional and compositional methods from texts.

This application is available under the agreement of the Apache License 2.0.

News

• 2012/03/30: Releasing TTC Term Suite version 1.2 (see ChangeLog).
• 2012/03/14: Releasing TTC Term Suite version 1.1 (see ChangeLog).
• 2012/03/03: Releasing TTC Term Suite version 1.0 (see ChangeLog).

Usage

First, please check that are installed on your computer by yourself:

• a Java 6 Runtime Environment (Sun or OpenJDK),
• the part-of-speech tagger and lemmatizer TreeTagger.

You also have to download the TTC Term Suite 1.2 executable Java archive and open it within a Java 6 Runtime Environment or by the help of the following command line:

java -jar ttc-term-suite-1.2.jar

Thanks

TTC Term Suite is powered by:

• the Java programming language and runtime environment,
• the framework Apache UIMA,
• the part-of-speech tagger and lemmatizer TreeTagger,
• the Java library tt4j for embedding TreeTagger in Java.

Community

If you enjoy this tool, register you as user on Ohloh please.