- (McCallum, 1999) ⇒ Andrew McCallum. (1999). “Multi-label Text Classification with a Mixture Model Trained by EM.” In: AAAI 99 Workshop on Text Learning.
- ~232 http://scholar.google.com/scholar?q=%22Multi-label+Text+Classification+with+a+Mixture+Model+Trained+by+EM%22+1999
text classification, Expectation-Maximization, integrating supervised and unsupervised learning, combining labeled and unlabeled data, Bayesian learning.
In many important document classification tasks, documents may each be associated with multiple class labels. This paper describes a Bayesian classification approach in which the multiple classes that comprise a document are represented by a mixture model. While the labeled training data indicates which classes were responsible for generating a document, it does not indicate which class was responsible for generating each word. Thus we use EM to ll in this missing value, learning both the distribution over mixture weights and the word distribution in each class's mixture component. We describe the benets of this model and present preliminary results with the Reuters-21578 data set. 1
|1999 MultilabelTextClassification||Andrew McCallum||Multi-label Text Classication with a Mixture Model Trained by EM||AAAI 99 Workshop on Text Learning||http://www.cs.umass.edu/~mccallum/papers/multilabel-nips99s.ps||1999|