Statistical language detector
Python
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.
scripts
.gitignore
MANIFEST.in
README.txt
setup.py
trilang.py

README.txt

--------------------------------------------------------------------------------
                    trilang -- Statistical language detector
--------------------------------------------------------------------------------

trilang is a statistical language detector. To detect the language of a text it
divides it into trigrams (blocks of three letters) and compares their frequency
with reference values in its database. The database is initially empty and has
to be filled by learning from texts with known languages.

The statistical approach has been described in the article "A Statistical
Approach to the Spam Problem" by Gary Robinson, 1 Mar 2003, Linux Journal,
http://www.linuxjournal.com/article/6467 .


Contact

Please email me with any comments or questions you have:
Hermann Schwarting <trilang@knackich.de>