Abstract | ||
---|---|---|
The goal of the document routing task is to extrapolate from documents judged relevant or ir- relevant for each of a set of topics accurate procedures for a ssessing the relevance of future documents for each topic. Rather than viewing different approaches to this problem as "winner- takes-all" competitors, we view them as potentially comple mentary methods, each exploiting different sources of information. This paper describes two quite different machine-learning ap- proaches to the document routing task, and two approaches to combining their results to per- form relevance assessments on new documents. We also describe an approach to the the con- fusion task based on n-grams that allow approximate matches. |
Year | Venue | Keywords |
---|---|---|
1996 | TREC | data fusion,machine learning,winner take all |
Field | DocType | Citations |
Data mining,Confusion,Information retrieval,Computer science,Document representation,Sensor fusion,Artificial intelligence,Natural language processing,Schema (psychology),Machine learning,Competitor analysis | Conference | 7 |
PageRank | References | Authors |
2.64 | 9 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kwong Bor Ng | 1 | 110 | 13.37 |
David Loewenstern | 2 | 86 | 12.73 |
Chumki Basu | 3 | 574 | 160.00 |
Haym Hirsh | 4 | 1839 | 277.74 |
Paul B. Kantor | 5 | 716 | 115.67 |