@inproceedings{1281255, added-at = {2008-01-15T05:49:09.000+0100}, address = {New York, NY, USA}, author = {Sandler, Mark}, biburl = {http://www.bibsonomy.org/bibtex/24ce9a832df16ba8a0c876b9c71c8461d/pitman}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, description = {Hierarchical mixture models}, doi = {http://doi.acm.org/10.1145/1281192.1281255}, interhash = {391b6d30ae1a0aca4f4d178b2f504fce}, intrahash = {4ce9a832df16ba8a0c876b9c71c8461d}, isbn = {978-1-59593-609-7}, keywords = {classification ml}, location = {San Jose, California, USA}, pages = {580--589}, publisher = {ACM}, timestamp = {2008-01-15T05:49:09.000+0100}, title = {Hierarchical mixture models: a probabilistic analysis}, url = {http://portal.acm.org/citation.cfm?doid=1281192.1281255}, year = 2007 } @book{MR2051784, added-at = {2008-01-15T01:27:53.000+0100}, address = {Amsterdam}, biburl = {http://www.bibsonomy.org/bibtex/2e1c6f29f7a54860167cbfd035f31eb39/pitman}, coden = {TCSDI}, description = {MR lookup}, editor = {Abe, N. and Khardon, R.}, interhash = {71a263d390b53eb72fdf4ac05aecd69d}, intrahash = {e1c6f29f7a54860167cbfd035f31eb39}, issn = {0304-3975}, keywords = {algorithmic learning ml theory}, mrclass = {68-06 (68Q32 68T05)}, mrnumber = {MR2051784}, note = {Papers from the 12th Annual Conference (ALT'01) held in Washington, DC, November 25--28, 2001, Theoret. Comput. Sci. {\bf 313} (2004), no. 2}, pages = {i--iv and 173--}, publisher = {Elsevier Science Publishers B.V.}, timestamp = {2008-01-15T01:27:53.000+0100}, title = {Algorithmic learning theory}, year = 2004 } @inproceedings{1255243, abstract = {Name ambiguity is a special case of identity uncertainty where one person can be referenced by multiple name variations in different situations or even share the same name with other people. In this paper, we focus on the problem of disambiguating person names within web pages and scientific documents. We present an efficient and effective two-stage approach to disambiguate names. In the first stage, two novel topic-based models are proposed by extending two hierarchical Bayesian text models, namely Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA). Our models explicitly introduce a new variable for persons and learn the distribution of topics with regard to persons and words. After learning an initial model, the topic distributions are treated as feature sets and names are disambiguated by leveraging a hierarchical agglomerative clustering method. Experiments on web data and scientific documents from CiteSeer indicate that our approach consistently outperforms other unsupervised learning methods such as spectral clustering and DBSCAN clustering and could be extended to other research fields. We empirically addressed the issue of scalability by disambiguating authors in over 750,000 papers from the entire CiteSeer dataset. }, acm = {http://portal.acm.org/citation.cfm?id=1255243}, added-at = {2008-01-09T01:08:56.000+0100}, address = {New York, NY, USA}, author = {Song, Yang and Huang, Jian and Councill, Isaac G. and Li, Jia and Giles, C. Lee}, biburl = {http://www.bibsonomy.org/bibtex/2624d2a29008c475245aa0bca052e7c0f/pitman}, booktitle = {JCDL '07: Proceedings of the 2007 conference on Digital libraries}, description = {Efficient topic-based unsupervised name disambiguation}, doi = {http://doi.acm.org/10.1145/1255175.1255243}, interhash = {e82d8ac4a42c2199149348551bbad51d}, intrahash = {624d2a29008c475245aa0bca052e7c0f}, isbn = {978-1-59593-644-8}, keywords = {ml}, location = {Vancouver, BC, Canada}, pages = {342--351}, publisher = {ACM}, timestamp = {2008-01-09T01:08:56.000+0100}, title = {Efficient topic-based unsupervised name disambiguation}, url = {http://clgiles.ist.psu.edu/papers/JCDL2007-topic_based_name_disambiguation.pdf }, year = 2007 } @unpublished{giles08gsk, added-at = {2008-01-09T00:18:12.000+0100}, author = {et al, C.L. Giles}, biburl = {http://www.bibsonomy.org/bibtex/2b2e5eae7c1cc273831d431b2c833f835/pitman}, interhash = {6900a8fc201e8cf0ce0577cee552c82f}, intrahash = {b2e5eae7c1cc273831d431b2c833f835}, keywords = {ml}, timestamp = {2008-01-09T00:18:12.000+0100}, title = {Generating Summary Keywords for Emails Using Topics}, url = {http://www.seas.upenn.edu/~mdredze/publications/dredze_summarization_iui08.pdf}, year = 2008 }