I spent the afternoon creating a formalized mapping from RelEx and Wordnet to OpenCog. The goal is to clean things up enough so that I can run word-sense disambiguation code with opencog itself. Now, one thing that was nagging me is that this is, in some sense, the hard-way forward — I could just download Rada Mihalcea’s WSD code from off the net, and just run that. But this misses the point: I want to have the network graph of word senses within opencog so that I can start trying to resolve senses across multiple sentences, and thus, potentially do document-level word-sense detection. So I’m pretty excited by the approach, but it sure does feel like re-inventing the wheel,. sometimes. I hope to post the spec to opencog-discuss in a few days.
Support OpenCog
-
Recent Posts
Activity
-
RT @dhart: OpenCog Foundation accepted for Google Summer of Code 2012 https://t.co/x0dulUrD #GSOC #OpenCog— March 17th via Twitter
-
RT @ferrouswheel: On that note, the HK @opencog project is looking for developers: http://t.co/tAxsT5yD— October 22nd via Twitter
-
RT @ferrouswheel: Amused to find out people are making predictions about whether @opencog will reach v1.0 in Dec 2012.— October 22nd via Twitter
-
Videos of what we've been working on http://t.co/qATDqQR— August 4th via Twitter
-
— May 29th via Youtube
-
OpenCog Recap for May 2011: http://blog.opencog.org/2011/05/20/opencog-recap-may-2011/ #ai #machinelearning— May 20th via Twitter
-
OpenCog now has Python bindings thanks to @ferrouswheel http://wiki.opencog.org/w/Python— May 16th via Twitter
-
Recent Comments
- Linas Vepstas on Genetic Crossover in MOSES
- Nil Geisweiller on Genetic Crossover in MOSES
- chhean on Tuning Metalearning in MOSES
- Rob on Determining word senses from grammatical usage
- J P on Tuning Metalearning in MOSES
Archives
Categories
Meta