News for hackers. Stuff that matters.
Re:Python NLTK Bayesian Classifier for word sense disambigua... by cybernytrix on Wednesday December 01, 2010 @02:21AM (#1957165)
I'm surprised that no one mentioned this paper that first evaluated this approach to using Wikipedia data: http://www.aaai.org/Papers/IJCAI/2007/IJCAI07-259.pdf That said, the major drawback of using Wikipedia is the size. If this approach is to be used for all words (not just Apple) then the total training corpus will be several GBs. Definitely not practical...
Re:Python NLTK Bayesian Classifier for word sense disambigua... by nl on Wednesday December 01, 2010 @05:46AM (#1957470)
What's not practical about it?

GBs of data are pretty easy to handle these days

Re:Python NLTK Bayesian Classifier for word sense disambigua... by cybernytrix on Wednesday December 01, 2010 @07:52PM (#1960483)
GBs and TBs of data is common, not for this task. All you are doing is Word Sense Disambiguation and there are algorithms to do WSD that work with much much smaller training sets. Just don't think that the exponential increase in training data is justified...