UMIACS Computational Linguistics Colloquium

March 3, 2004, 11:00am, AVW Room 2120

It is known that context words tend to be self-triggers, that is, the probability of a content word to appear more than once in a document, given that it already appears once, is significantly higher than the probability of the first occurrence. We look at self-trigger ability across hyperlinks on the Web. We show that the probability of a word w_j to appear in a Web document d_i depends on the presence of w_jin documents pointing to d_i.

We back our claim using two experiments which deal with single word and two word queries from the query log of a major commercial search engine and discuss the implications of the findings to Document Modeling and Information Retrieval. In Document Modeling, we will propose the use of a correction factor, $R$, which indicates how much more likely a word is to appear in a document given that another document containing the same word is linked to it. In Information Retrieval, we suggest the concept of a document closure which can be automatically computed in order to identify words that are not present in a document, but by virtue of their presence in documents linked to the document, should be added to the index for it.

About the Speaker:

Dragomir R. Radev is an Assistant Professor of Information, Electrical Engineering and Computer Science, and Linguistics at the University of Michigan, Ann Arbor. He holds a Ph.D. in Computer Science from Columbia University. Before joining Michigan, he was a Research Staff Member at IBM's TJ Watson Research Center in Hawthorne, NY. He is the author of more than 45 papers on text summarization; question answering, machine translation, text generation, information extraction, and information retrieval. Dr Radev's current research on probabilistic and link-based methods for exploiting very large textual repositories, representing and acquiring knowledge of genome regulation, and semantic entity and relation extraction from Web-scale text document collections is supported by NSF and NIH. He serves on the HLT-NAACL advisory committee, was recently reelected as treasurer of NAACL, is a member of the editorial boards of JAIR and Information Retrieval, and is a four-time finalist at the ACM programming finals (as contestant in 1993 and as coach in 1995-1997). Additional information is available at http://tangra.si.umich.edu/clair/

For the colloquium series schedule, see the UMD Computational http://www.umiacs.umd.edu/research/CLIP/colloq/. If you are interested in meeting with the speaker, please contact Doug <http://www.glue.umd.edu/~oard/> Oard (oard@umiacs.umd.edu

<mailto:oard@umiacs.umd.edu> ).