@inproceedings{cf6a4d94ad2d4949837d637487a39d17,
title = "Document-topic hierarchies from document graphs",
abstract = "Topic taxonomies present a multi-level view of a document collection, where general topics live towards the top of the taxonomy and more specific topics live towards the bottom. Topic taxonomies allow users to quickly drill down into their topic of interest to find documents. We show that hierarchies of documents, where documents live at the inner nodes of the hierarchy-tree can also be inferred by combining document text with inter-document links. We present a Bayesian generative model by which an explicit hierarchy of documents is created. Experiments on three document-graph data sets shows that the generated document hierarchies are able to fit the observed data, and that the levels in the constructed document hierarchy represent practical groupings.",
keywords = "bayesian generative models, hierarchical clustering, model evaluation, topic models",
author = "Tim Weninger and Yonatan Bisk and Jiawei Han",
year = "2012",
doi = "10.1145/2396761.2396843",
language = "English (US)",
isbn = "9781450311564",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "635--644",
booktitle = "CIKM 2012 - Proceedings of the 21st ACM International Conference on Information and Knowledge Management",
address = "United States",
note = "21st ACM International Conference on Information and Knowledge Management, CIKM 2012 ; Conference date: 29-10-2012 Through 02-11-2012",
}