@techreport{oai:ipsj.ixsq.nii.ac.jp:00059087,
 author = {Hong-WooChun and Yoshimasa, Tsuruoka and Jun'ichi, Tsujii and Hong-Woo, Chun and Yoshimasa, Tsuruoka and Jun'ichi, Tsujii},
 issue = {128(2005-BIO-003)},
 month = {Dec},
 note = {We extracted disease-gene relations from MedLine using disease/gene dictionaries which are constructed from six public DBs. Since dictionary matching produces a large number of false positives  we developed a method of machine learning-based named entity recognition (NER) to filter out false recognitions of disease/gene names. We found that the performance of relation extraction depends on the performance of NER filtering and that the filtering improves the precision of relation extraction by 26.7% at the cost of a small reduction in recall., We extracted disease-gene relations from MedLine using disease/gene dictionaries which are constructed from six public DBs. Since dictionary matching produces a large number of false positives, we developed a method of machine learning-based named entity recognition (NER) to filter out false recognitions of disease/gene names. We found that the performance of relation extraction depends on the performance of NER filtering and that the filtering improves the precision of relation extraction by 26.7% at the cost of a small reduction in recall.},
 title = {Disease-gene relations extraction using domain dictionaries and named entity recognition filtering},
 year = {2005}
}