Graded Relevance is a relevance assessment framework in information retrieval that categorizes retrieved documents into multiple ordered levels of relevance, distinguishing it from binary relevance by allowing fine-grained, non-binary judgments reflecting varying degrees of topical or contextual appropriateness to the user query.
46
Publications
7.9K
Citations
108
Authors
55
Institutions
Publications per year
2017–2026
10
Publications
46
Expected reciprocal rank for graded relevance
Olivier Chapelle, Donald Metlzer, Ya Zhang et al. · 2009 · 839 citations
Evaluating evaluation metrics based on the bootstrap
Tetsuya Sakai · 2006 · 210 citations
1–5 of 46
Authors
108
- TS
10
h-index
- SR
3
h-index
- RS
3
h-index
- KJ
3
h-index
- JK
3
h-index
1–5 of 108
Institutions
55
Tampere University
Tampere, Finland
6 h-index
9 publications
10.1K citations
Toshiba (Japan)
Tokyo, Japan
3 h-index
3 publications
482 citations
Microsoft Research Asia (China)
Beijing, China
3 h-index
4 publications
389 citations
Microsoft (United States)
Redmond, United States
3 h-index
8 publications
359 citations
Association for Computing Machinery
New York, United States
2 h-index
2 publications
72 citations
Google (United States)
Mountain View, United States
2 h-index
5 publications
1.2K citations
Microsoft Research (United Kingdom)
Cambridge, United Kingdom
2 h-index
3 publications
246 citations
Tsinghua University
Beijing, China
2 h-index
10 publications
144 citations
1–8 of 55
Venues
- Information Processing & Management
6 publications · 322 citations
6
h-index
- arXiv (Cornell University)
Repository · 2 publications · 35 citations
2
h-index
- Journal of the American Society for Information Science and Technology
JASIST · 2 publications · 300 citations
2
h-index
- ACM Transactions on Information Systems
1 publications · 4.6K citations
1
h-index
- Online Information Review
1 publications · 14 citations
1
h-index
1–5