A finite-state based lemmatizing, tagging, and spelling library in Java. Additionally, it includes a Polish morphosyntactic dictionary used for part-of-speech tagging.
Ikulo is a fun project. It could become a server process which watches a folder for new music files and could tag, rename and move those files using data from MusicBrainz. An additional desktop client (ie. for non matched files) could be created.
Citar is a C++ free software part of speech tagger using a trigram Hidden Markov Model (HMM), with linear interpolation smoothing of trigrams and suffix-based unknown word handling.
Features
Citar has the following major features:
* High accuracy tagging through a trigram Hidden Markov
... [More] Model with Viterbi decoding.
* Handling of unknown words through suffix analysis.
* Licensed under the GNU Lesser General Public License version 2.1 (LGPLv2.1), which only imposes restrictions on redistribution of Citar itself.
* Written in C++ for performance. [Less]
JitarJitar is an open source part of speech tagger using a trigram Hidden Markov Model (HMM).
FeaturesJitar has the following major features:
High accuracy tagging through a trigram Hidden Markov Model with Viterbi decoding. Handling of unknown words through suffix analysis. Licensed under
... [More] the GNU Lesser General Public License version 3 (LGPLv3), which only imposes restrictions on redistribution of Jitar itself. Written in Java, allowing for easy integration with other programs that are built upon the excellent JDK platform. AvailabilityJitar 0.0.2 is now available, and can be obtained in source or compiled form from the Downloads page. You can also use Subversion to retrieve this version of Jitar:
svn checkout http://jitar.googlecode.com/svn/tags/jitar-0.0.2After checking out or dow [Less]
This site uses cookies to give you the best possible experience.
By using the site, you consent to our use of cookies.
For more information, please see our
Privacy Policy