• Statistical Information Extraction

Courses

• Information Retrieval Course
• Advanced Topics In Information Retrieval

Fall 2002

NOTE THE DATES SO YOU GET THE CORRECT WEEK

For November 4

• "Latent Dirichlet allocation". D. M. Blei, A. Y. Ng, and M. I. Jordan. Technical Report UCB//CSD-02-1194. This paper is available in two forms: read them both. Note that this paper may be particularly challenging, but do your best. PS.gz, 30 pages and PS.gz, 8 pages
• There is no additional paper this week; these will be challenging enough.

For October 28

• "Probabilistic Models of Text and Link Structure for Hypertext Classification", L. Getoor, E. Segal, B. Taskar, D. Koller. IJCAI01 Workshop on Text Learning: Beyond Supervision, Seattle, Washington, August 2001. PS That version seems to print badly (the margins are messed up). Here is a version in PDF that has the margins stripped off. Make sure when you print it you select "center page" or whatever the option is. PDF without margins * Taskar, B., E. Segal and D. Koller. (2002). Discriminative Probabilistic Models for Relational Data, Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI02), Edmonton, Canada. [online|http://robotics.stanford.edu/~btaskar/]

For October 21

• Djoerd Hiemstra, "Term-Specific Smoothing for the Language Modeling Approach to Information Retrieval:The Importance of a Query Term ." In SIGIR 2002, pp 35-41 [PDF|http://wwwhome.cs.utwente.nl/~hiemstra/papers/sigir02lm.pdf]
• John Canny, "Collaborative Filtering with Privacy via Factor Analysis", In SIGIR 2002, pp 238-245[PDF|http://www.cs.berkeley.edu/~jfc/papers/02/SIGIR02.pdf]

For October 16 (Wednesday, but Monday class schedule)

• Si and Callan, "Using sampled data and regression to merge search engine results." In SIGIR 2002, pp 19-26. [[PS|http://www-2.cs.cmu.edu/~callan/Papers/sigir02-lsi.ps]
• Si, Jin, Callan, and Ogilvie, "Language modeling framework for resource selection and results merging." To appear in CIKM 2002. [PS|http://www-2.cs.cmu.edu/~callan/Papers/cikm02-lsi.ps]

For October 14

• ''October 14th is a holiday. Class will meet on the 16th,which is a Wednesday, but a Monday class schedule.''

For October 7

• Bennett, Dumais, and Horvitz. "Probabilistic combination of text classifiers using reliability indicators: models and results." In SIGIR 2002, pp 207-214. [PDF|http://research.microsoft.com/~sdumais/SIGIR2002-Combo.pdf]
• Federico and Bertoldi. "Statistical cross-language information retrieval using N-best query translations." In SIGIR 2002, pp. 167-174. Get the [PDF via the ACM portal|http://doi.acm.org/10.1145/564376.564407]

For September 30 *John Lafferty and Chengxiang Zhai. "Probabilistic relevance models based on document and query generation," In Proceedings of the Workshop on Language Modeling and Information Retrieval, Carnegie Mellon University, 2001, [PS|http://www.cs.cmu.edu/~lafferty/ps/dq.ps] (''this is different from the document on the language modeling workshop page'')

• S. Robertson, "On Bayesian models and event spaces in information retrieval." Presented at MF/IR Workshop of SIGIR 2002.[PDF| http://research.microsoft.com/users/robertson/papers/bayes_models.pdf] (older versions...[PDF|http://dcs.vein.hu/CIR/cikkek/Bayes_models.pdf],[HTML|http://citeseer.nj.nec.com/529095.html])

For September 23

• C.Zhai and J. Lafferty, "Two-Stage language models for information retrieval." Appears in SIGIR 2002, pp. 49-56. [PS|http://www-2.cs.cmu.edu/%7Elafferty/ps/two-stage.ps]
• Y. Zhang, J. Callan, and T. Minka, "Novelty and redundancy detection in adaptive filtering." Appears in SIGIR 2002, pp. 81-88. [PS|http://www-2.cs.cmu.edu/%7Ecallan/Papers/sigir02-yiz.ps]

September 16

• Title Language Model for Information Retrieval by R. Jin, A.G. Hauptmann, and C. Zhai, Carnegie Mellon University. Appears in SIGIR 2002, pp. 42-47. [PDF|http://www.cs.cmu.edu/%7Eczhai/paper/sigir2002-titlemod.pdf]
• W. Kraaij, T. Westerveld, and D. Hiemstra, " The Importance of prior probabilities for entry page search ." SIGIR 2002, pp. 27-34. [HTML|http://wwwhome.cs.utwente.nl/%7Ewesterve/sigirEPpriors.html]

Papers under consideration. Feel free to add suggestions, providing a link to the paper and preferably some thoughts about why you think it'd be interesting.

* "Expectation-propagation for the generative aspect model", John Lafferty and Thomas Minka. Uncertainty in Artificial Intelligence (UAI), 2002 [ps|http://www.cs.cmu.edu/~lafferty/ps/aspect.ps]

• C. Dwork, R. Kumar, M. Naor, and D. Sivakumar, "Rank Aggregation Methods for the Web." World Wide Web 2001. [HTML|http://citeseer.nj.nec.com/dwork01rank.html]
• Stephen Robertson and Djoerd Hiemstra,"Language Models and Probability of Relevance," In Proceedings of the Workshop on Language Modeling and Information Retrieval, Carnegie Mellon University, 2001,[PDF|http://la.lti.cs.cmu.edu/callan/Workshops/lmir01/WorkshopProcs/Papers/ser.pdf]
• Fernando Pereira. Formal Grammar and Information Theory: Together Again?. Philosophical Transactions of the Royal Society, 358(1769):1239-1253, April 2000.[PDF|http://www.cis.upenn.edu/~pereira/papers/rsoc.pdf]
• Christopher J. C. Burges, (1998). A Tutorial on Support Vector Machines for Pattern Recognition [CiteSeerLink | http://citeseer.nj.nec.com/burges98tutorial.html]
• "Optimal Mixture Models in IR", Lavrenko, V., in the Proceedings of the 24'th European Colloquium on IR Research (ECIR'02), Glasgow, Scotland, March 25-27, 2002. [PDF|http://ciir.cs.umass.edu/~lavrenko/pub/OptimalMixtureModels.pdf]
• A. Berger and J. Lafferty. Information Retrieval as Statistical Translation. In Proceedings of SIGIR-99, Berkeley, CA, August 1999. [CiteSeerLink|http://citeseer.nj.nec.com/berger99information.html]

[James's page|http://ciir.cs.umass.edu/cmpsci791h] (now hopelessly out of date)

-- AndreGauthier - 28 Oct 2002