Abstract | ||
---|---|---|
The use of large-scale experimental techniques and biomedical tools has increased the pace at which biologists produce useful information. This promotes us to propose a Bayesian model for learning and re-ranking to boost genomics information retrieval performance. We first describe a general model for discovering the property of each passage. Then, we examine a Bernoulli distribution as the prior distribution and provide an efficient way to obtain the training passages for parameter estimation, according to the characterizations of the Bernoulli distribution. Later, we evaluate our proposed model by conducting extensive experiments on the TREC 2007 and 2006 Genomics data sets. The experimental results show the effectiveness of the proposed model for improving performance on two years' TREC Genomics data sets. Furthermore, the conclusions and future prospects are also discussed. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1854776.1854846 | BCB |
Keywords | Field | DocType |
general model,large-scale experimental technique,genomics data set,bernoulli distribution,genomics information retrieval,prior distribution,genomics information retrieval performance,trec genomics data set,bayesian model,bayesian inference,parameter estimation,information retrieval,genomics | Data mining,Data set,Bayesian inference,Computer science,Genomics,Artificial intelligence,Estimation theory,Bernoulli distribution,Information retrieval,Ranking,Bioinformatics,Prior probability,TREC Genomics,Machine learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 7 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qinmin Vivian Hu | 1 | 20 | 6.06 |
Xiangji Huang | 2 | 1551 | 159.34 |