论文信息 - The TREC-5 Filtering Track

The TREC-5 Filtering Track

The Trec-5 filtering track, an evaluation of binary text classification systems, was a repeat of the filtering evaluation run in a trial version for TREC-4, with only the data set and participants changing. Seven sites took part, submitting a total of ten runs. We review the nature of the task, the effectiveness measures and evaluation methods used, and briefly discuss the results. Some deficiencies in the evaluation are examined, with an eye toward improving future filtering evaluations

David D. Lewis | D. Lewis

[1] William A. Gale,et al. A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[2] Peter E. Hart,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[3] H. J. Arnold. Introduction to the Practice of Statistics , 1990 .

[4] Hinrich Schütze,et al. Xerox Site Report: Four TREC-4 Tracks , 1995, TREC.

[5] Paul S. Jacobs. GE in TREC-2: Results of a Boolean Approximation Method for Routing and Retrieval , 1993, TREC.

[6] David D. Lewis,et al. Evaluating Text Categorization I , 1991, HLT.

[7] S. Robertson. The probability ranking principle in IR , 1997 .

[8] David D. Lewis,et al. Evaluating and optimizing autonomous text classification systems , 1995, SIGIR '95.

[9] Donna K. Harman,et al. Overview of the Fourth Text REtrieval Conference (TREC-4) , 1995, TREC.

[10] Kui-Lam Kwok,et al. TREC-3 Ad-Hoc, Routing Retrieval and Thresholding Experiments using PIRCS , 1994, TREC.

[11] William S. Cooper,et al. On selecting a measure of retrieval effectiveness , 1973, J. Am. Soc. Inf. Sci..

[12] Richard M. Tong,et al. Machine Learning for Knowledge-Based Document Routing (A Report on the TREC-2 Experiment) , 1993, TREC.