Dynamic hierarchical Markov random fields and their application to web data extraction

Jun Zhu, Zaiqing Nie, Bo Zhang, Ji-Rong Wen
2007 Proceedings of the 24th international conference on Machine learning - ICML '07  
Hierarchical models have been extensively studied in various domains. However, existing models assume fixed model structures or incorporate structural uncertainty generatively. In this paper, we propose Dynamic Hierarchical Markov Random Fields (DHMRFs) to incorporate structural uncertainty in a discriminative manner. DHMRFs consist of two parts -structure model and class label model. Both are defined as exponential family distributions. Conditioned on observations, DHMRFs relax the
more » ... assumption as made in directed models. As exact inference is intractable, a variational method is developed to learn parameters and to find the MAP model structure and label assignment. We apply the model to a real-world web data extraction task, which automatically extracts product items for sale on the Web. The results show promise.
doi:10.1145/1273496.1273644 dblp:conf/icml/ZhuNZW07 fatcat:hgdcvpczc5dv3konp2nia7vycq