Skip to content
A simple cross-lingual world sense disambiguator based on Weka and Europarl data
Java
Find file
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.
lib
src Add the classifier package
LICENSE.txt
README

README

The goal of this project is to implement a simple cross-lingual WordSense
Disambiguator that takes data from EuroParl, parse them, postprocess them in
order to reduce the noise and convert them to ARFF file format, so that Weka
can use them to build a classifier.

Note that a classifier can disambiguate just _one_ word.

DEPENDENCIES:
* commons-logging
* commons-configuration
* snowball (for stemming) [optional with minor code changes]

Something went wrong with that request. Please try again.