Name
Abstract | ||
|---|---|---|
In this paper, we focus on the biomedicine domain to propose a multi-source fusion approach for improving information retrieval performance. First, we consider a common scenario for a metasearch system that has access to multiple baselines with retrieving and ranking documents/passages by their own models. Second, given selected baselines from multiple sources, we employ two modified fusion rules in the proposed approach, reciprocal and combMNZ, to rerank the candidates as the output for evaluation. Third, our empirical study on both 2007 and 2006 genomics data sets demonstrates the viability of the proposed approach to better performance fusion. Fourth, the experimental results show that the reciprocal method provides notable improvements on the individual baseline, especially on the effective passage MAP, the passage2-level and the diversity MAP, the aspect-level. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/BIBM.2010.5706649 | BIBM |
Keywords | Field | DocType |
bioinformatics,genomics,information retrieval,medical information systems,biomedicine domain,genomics,information retrieval performance,metasearch system,multiple sources,multisource fusion approach,reciprocal method,CombMNZ,Ge-nomics,Information Retrieval,Multi-source Fusion,Reciprocal | Information system,Reciprocal,Data mining,Metasearch engine,Information retrieval,Ranking,Computer science,Fusion rules,Biomedicine,Bioinformatics,Multi-source,Empirical research | Conference |
ISSN | Citations | PageRank |
2156-1125 | 1 | 0.36 |
References | Authors | |
12 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qinmin Vivian Hu | 1 | 20 | 6.06 |
| Xiangji Huang | 2 | 1551 | 159.34 |
| Jun Miao | 3 | 9 | 1.10 |