Supervised Disambiguation: Bayesian Classification II
Naïve Bayes assumption: P(C|sk) = P({vj| vj in C}| sk) = ? vj in CP(vj | sk)
The Naïve Bayes assumption is incorrect in the context of text processing, but it is useful.
Decisionrule for Naïve Bayes: Decide s’ if s’=argmax sk [log P(sk)+? vj in C log P(vj |sk)]
P(vj |sk) and P(sk) are computed via Maximum-Likelihood Estimation, perhaps with appropriate smoothing, from the labeled training corpus.