Abstract
We introduce an evaluation metric called P-measure for the task of retrieving one highly relevant document. It models user behaviour in practical tasks such as known-item search, and is more stable and sensitive than Reciprocal Rank which cannot handle graded relevance.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Twenty-Ninth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval |
| Pages | 695-696 |
| Number of pages | 2 |
| Publication status | Published - 2006 Oct 31 |
| Event | 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval - Seatttle, WA, United States Duration: 2006 Aug 6 → 2006 Aug 11 |
Publication series
| Name | Proceedings of the Twenty-Ninth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval |
|---|---|
| Volume | 2006 |
Conference
| Conference | 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval |
|---|---|
| Country | United States |
| City | Seatttle, WA |
| Period | 06/8/6 → 06/8/11 |
Fingerprint
Keywords
- Evaluation metrics
- Test collection
ASJC Scopus subject areas
- Engineering(all)
- Information Systems
- Software
- Applied Mathematics
Cite this
Sakai, T. (2006). Give me just one highly relevant document: P-measure. In Proceedings of the Twenty-Ninth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 695-696). (Proceedings of the Twenty-Ninth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval; Vol. 2006).