Name
Abstract | ||
|---|---|---|
The naive Bayes assumption in text classification has the advantage of greatly simplifying maximum likelihood estimation of unknown class-conditional word occurrence probabilities. However, these estimates are usually modified by application of a heuristic parameter smoothing technique to avoid (over-fitted) null estimates. In this work, we advocate the reduction of the parameter domain instead of parameter smoothing. This leads to a constrained domain maximum likelihood estimation problem for which we provide an iterative algorithm that solves it optimally. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/s10044-009-0149-y | Pattern Analysis & Applications |
Keywords | Field | DocType |
maximum likelihood estimation � naive bayestext classificationparameter smoothing � karush-kuhn-tucker conditions,karush kuhn tucker,iterative algorithm,maximum likelihood estimate,naive bayes,maximum likelihood estimation,karush kuhn tucker conditions | Heuristic,Likelihood function,Naive Bayes classifier,Pattern recognition,Iterative method,Maximum likelihood,Smoothing,Artificial intelligence,Karush–Kuhn–Tucker conditions,Maximum likelihood sequence estimation,Mathematics | Journal |
Volume | Issue | ISSN |
13 | 2 | 1433-755X |
Citations | PageRank | References |
4 | 0.39 | 4 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jesús Andrés-Ferrer | 1 | 73 | 7.52 |
| alfons juan | 2 | 572 | 61.45 |