Text Classification from Labeled and Unlabeled Documents using EM


This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. This is important because in many text classification problems obtaining training labels is expensive, while large quantities of unlabeled documents are readily available. We introduce an algorithm for learning from labeled and unlabeled documents based on the combination of Expectation-Maximization (EM) and a naive Bayes classifier. The algorithm first trains a classifier using the available labeled documents, and probabilistically labels the unlabeled documents. It then trains a new classifier using the labels for all the documents, and iterates to convergence. This basic EM procedure works well when the data conform to the generative assumptions of the model. However these assumptions are often violated in practice, and poor performance can result. We present two extensions to the algorithm that improve classification accuracy under these conditions: (1) a weighting factor to modulate the contribution of the unlabeled data, and (2) the use of multiple mixture components per class. Experimental results, obtained using text from three different real-world tasks, show that the use of unlabeled data reduces classification error by up to 30%.

DOI: 10.1023/A:1007692713085

Extracted Key Phrases

14 Figures and Tables

Showing 1-10 of 49 references

The EM algorithm and extensions

  • G J Mclachlan, T Krishnan
  • 1997
Highly Influential
1 Excerpt

An evaluation of statistical approaches to text categorization

  • Y Yang
  • 1999
1 Excerpt
Showing 1-10 of 1,390 extracted citations
Citations per Year

2,675 Citations

Semantic Scholar estimates that this publication has received between 2,424 and 2,952 citations based on the available data.

See our FAQ for additional information.