The nested Chinese restaurant process and Bayesian nonparametric inference of topic hierarchies Export

@article{hlda-new, abstract = {We present the nested Chinese restaurant process (nCRP), a stochastic process which assigns probability distributions to infinitely-deep, infinitely-branching trees. We show how this stochastic process can be used as a prior distribution in a Bayesian nonparametric model of document collections. Specifically, we present an application to information retrieval in which documents are modeled as paths down a random tree, and the preferential attachment dynamics of the nCRP leads to clustering of documents according to sharing of topics at multiple levels of abstraction. Given a corpus of documents, a posterior inference algorithm finds an approximation to a posterior distribution over trees, topics and allocations of words to levels of the tree. We demonstrate this algorithm on collections of scientific abstracts from several journals. This model exemplifies a recent trend in statistical machine learning--the use of Bayesian nonparametric methods to infer distributions on flexible data structures.}, archivePrefix = {arXiv}, author = {Blei, David M. and Griffiths, Thomas L. and Jordan, Michael I.}, citeulike-article-id = {2430904}, citeulike-linkout-0 = {http://arxiv.org/abs/0710.0845}, citeulike-linkout-1 = {http://arxiv.org/pdf/0710.0845}, day = {27}, eprint = {0710.0845}, keywords = {hierarchicaltopicmodels, infinite\_mixturemodels, topicmodels}, month = {Aug}, posted-at = {2008-07-11 17:16:54}, priority = {2}, title = {The nested Chinese restaurant process and Bayesian nonparametric inference of topic hierarchies}, url = {http://arxiv.org/abs/0710.0845}, year = {2009} }

TY - JOUR ID - hlda-new L3 - citeulike-article-id:2430904 N2 - We present the nested Chinese restaurant process (nCRP), a stochastic process which assigns probability distributions to infinitely-deep, infinitely-branching trees. We show how this stochastic process can be used as a prior distribution in a Bayesian nonparametric model of document collections. Specifically, we present an application to information retrieval in which documents are modeled as paths down a random tree, and the preferential attachment dynamics of the nCRP leads to clustering of documents according to sharing of topics at multiple levels of abstraction. Given a corpus of documents, a posterior inference algorithm finds an approximation to a posterior distribution over trees, topics and allocations of words to levels of the tree. We demonstrate this algorithm on collections of scientific abstracts from several journals. This model exemplifies a recent trend in statistical machine learning--the use of Bayesian nonparametric methods to infer distributions on flexible data structures. TI - The nested Chinese restaurant process and Bayesian nonparametric inference of topic hierarchies KW - hierarchicaltopicmodels KW - infinite_mixturemodels KW - topicmodels AU - Blei, David AU - Griffiths, Thomas AU - Jordan, Michael PY - 2009/Aug/27/ UR - http://arxiv.org/abs/0710.0845 ER -