This is the first year that members of the Database and Information System Lab (DBIS) at University of Illinois at Chicago (UIC) participate in TREC. We participate in two tasks for the Web track: topic distillation and named page finding. Linkage information among documents as well as content information about documents is used in some of our submitted runs. We utilize the Okapi weighting scheme with some modification for documents and passages retrieval; the proximity of query terms in documents is also utilized for document ranking. The PageRank of a document is combined with the similarity of the document with the query to obtain an overall ranking of documents. A local linkage and URL analysis algorithm is employed for topic distillation. In the named page finding task, we combine the surrogate similarity with the document similarity in one run.
[1]
Taher H. Haveliwala.
Efficient Computation of PageRank
,
1999
.
[2]
Berthier A. Ribeiro-Neto,et al.
Link-based and content-based evidential information in a belief network model
,
2000,
SIGIR '00.
[3]
Stephen E. Robertson,et al.
Relevance weighting of search terms
,
1976,
J. Am. Soc. Inf. Sci..
[4]
Stephen E. Robertson,et al.
Okapi/Keenbow at TREC-8
,
1999,
TREC.
[5]
Sergey Brin,et al.
The Anatomy of a Large-Scale Hypertextual Web Search Engine
,
1998,
Comput. Networks.
[6]
Amit Singhal,et al.
A case study in web search using TREC algorithms
,
2001,
WWW '01.