@inproceedings{cea015e50ec34aab881967a5f7bc4401,
title = "Finding co-occurring topics in wikipedia article segments",
abstract = "Wikipedia is the largest online encyclopedia, in which articles form knowledgeable and semantic resources. Identical topics in different articles indicate that the articles are related to each other about topics. Finding such co-occurring topics is useful to improve the accuracy of querying and clustering, and also to contrast related articles. Existing topic alignment work and topic relevance detection are based on term occurrence. In our research, we discuss incorporating latent topics existing in article segments by utilizing Latent Dirichlet Allocation (LDA), to detect topic relevance. We also study how segment proximities, arising from segment ordering and hyperlinks, shall be incorporated into topic detection and alignment. Experimental data show our method can find and distinguish three types of co-occurrence.",
keywords = "LDA, Link, MLE, Wikipedia",
author = "Renzhi Wang and Jianmin Wu and Mizuho Iwaihara",
year = "2014",
month = jan,
day = "1",
language = "English",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "252--259",
editor = "Adam Jatowt and Edie Rasmussen and Kulthida Tuamsuk",
booktitle = "The Emergence of Digital Libraries - Research and Practices - 16th International Conference on Asia-Pacific Digital Libraries, ICADL 2014, Proceedings",
note = "16th International Conference on Asia-Pacific Digital Libraries, ICADL 2014 ; Conference date: 05-11-2014 Through 07-11-2014",
}