@techreport{hofmann1998statistical,
  abstract = {Modeling and predicting co-occurrences of events is a fundamental problem of unsupervised learning. In this contribution we develop a statistical framework for analyzing co-occurrence data in a general setting where elementary observations are joint occurrences of pairs of abstract objects from two finite sets. The main challenge for statistical models in this context is to overcome the inherent data sparseness and to estimate the probabilities for pairs which were rarely observed or even unobserved in a given sample set. Moreover, it is often of considerable interest to extract grouping structure or to find a hierarchical data organization. A novel family of mixture models is proposed which explain the observed data by a finite number of shared aspects or clusters. This provides a common framework for statistical inference and structure discovery and also includes several recently proposed models as special cases. Adopting the maximum likelihood principle, EM algorithms are derived to fit the model parameters. We develop improved versions of EM which largely avoid overfitting problems and overcome the inherent locality of EM--based optimization. Among the broad variety of possible applications, e.g., in information retrieval, natural language processing, data mining, and computer vision, we have chosen document retrieval, the statistical analysis of noun/adjective co-occurrence and the unsupervised segmentation of textured images to test and evaluate the proposed algorithms.},
  address = {Cambridge, MA, USA},
  author = {Hofmann, Thomas and Puzicha, Jan},
  file = {hofmann1998statistical.pdf:hofmann1998statistical.pdf:PDF},
  institution = {Massachusetts Institute of Technology},
  interhash = {f4d76aef2c16c571ee23fc04aac781c2},
  intrahash = {edca714d2bc0060e6f3e4e7e67df690b},
  lastdatemodified = {2007-03-13},
  lastname = {Hofmann},
  month = {February},
  own = {notown},
  pdf = {hofmann98_statistical.pdf},
  read = {notread},
  title = {Statistical Models for Co-occurrence Data},
  year = 1998
}