@article{pu2009latent, abstract = {Co-clustering has emerged as an important technique for mining contingency data matrices. However, almost all existing co-clustering algorithms are hard partitioning, assigning each row and column of the data matrix to one cluster. Recently a Bayesian co-clusteringapproach has been proposed which allows a probability distribution membership in row and column clusters. The approach usesvariational inference for parameter estimation. In this work, we modify the Bayesian co-clustering model, and use collapsedGibbs sampling and collapsed variational inference for parameter estimation. Our empirical evaluation on real data sets showsthat both collapsed Gibbs sampling and collapsed variational inference are able to find more accurate likelihood estimatesthan the standard variational Bayesian co-clustering approach.}, author = {Wang, Pu and Domeniconi, Carlotta and Laskey, Kathryn}, interhash = {ca3c6ea6255fd4fa4601502fd55bec24}, intrahash = {0ef1833cdcdf2a7d9093e37894c4f3ab}, journal = {Machine Learning and Knowledge Discovery in Databases}, pages = {522--537}, title = {Latent Dirichlet Bayesian Co-Clustering}, url = {http://dx.doi.org/10.1007/978-3-642-04174-7_34}, year = 2009 } @inproceedings{PuWang:2007, abstract = {The exponential growth of text documents available on the Internet has created an urgent need for accurate, fast, and general purpose text classification algorithms. However, the "bag of words" representation used for these classification methods is often unsatisfactory as it ignores relationships between important terms that do not co-occur literally. In order to deal with this problem, we integrate background knowledge - in our application: Wikipedia - into the process of classifying text documents. The experimental evaluation on Reuters newsfeeds and several other corpus shows that our classification results with encyclopedia knowledge are much better than the baseline "bag of words " methods.}, author = {Wang, Pu and Hu, Jian and Zeng, Hua-Jun and Chen, Lijun and Chen, Zheng}, booktitle = {Data Mining, 2007. ICDM 2007. Seventh IEEE International Conference on}, doi = {10.1109/ICDM.2007.77}, interhash = {8a899b60047e20e162fc12b2ff6f8142}, intrahash = {66058efbca5abd1222f72c32365d23fa}, isbn = {978-0-7695-3018-5}, issn = {1550-4786}, pages = {332-341}, title = {Improving Text Classification by Using Encyclopedia Knowledge}, url = {ftp://ftp.computer.org/press/outgoing/proceedings/icdm07/Data/3018a332.pdf}, year = 2007 }