Abstract | ||
---|---|---|
Cosine Pivoted Document Length Normalization has reached a point of stability where many researchers indiscriminately apply a specific value of 0.2 regardless of the collection. Our efforts, however, demonstrate that applying this specific value without tuning for the document collection degrades average precision by as much as 20%. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1145/564376.564454 | SIGIR |
Keywords | Field | DocType |
specific value,document collection,cosine pivoted document length,document normalization,average precision,text search,information retrieval | Data mining,Normalization (statistics),Pattern recognition,Information retrieval,Similarity measure,Computer science,Full text search,Relevance measure,Artificial intelligence | Conference |
ISBN | Citations | PageRank |
1-58113-561-0 | 18 | 1.33 |
References | Authors | |
2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Abdur Chowdhury | 1 | 2013 | 160.59 |
M. Catherine McCabe | 2 | 91 | 7.85 |
David Grossman | 3 | 525 | 34.73 |
Ophir Frieder | 4 | 3300 | 419.55 |