Automatic extraction of data deposition statements: where do the research results go?
暂无分享,去创建一个
Research in the biomedical domain can have a major impact through open sharing of data produced. In this study, we use machine learning for the automatic identification of data deposition sentences in research articles. Articles containing deposition sentences are correctly identified with 73% f-measure. These results show the potential impact of our method for literature curation.
[1] Daniel X. Le,et al. Naïve Bayes and SVM classifiers for classifying databank accession number sentences from online biomedical articles , 2010, Electronic Imaging.
[2] Wendy W. Chapman,et al. Identifying Data Sharing in Biomedical Literature , 2008, AMIA.
[3] Christian J Stoeckert,et al. Much room for improvement in deposition rates of expression microarray datasets , 2008, Nature Methods.