BMC Bioinformatics

Table 3 Performance of relation recognition.

From: Automatic recognition of topic-classified relations between prostate cancer and genes using MEDLINE abstracts

	Features					Precision (%)	Relative recall (%)
	Order of entities	Bag of words	Candidate entities	Unigram	Bigram
Any relation						0.907	0.958
						0.908	0.957
						0.896	0.975
						0.902	0.957
						0.903	0.966
						0.909	0.961
Study description						0.669	0.567
						0.650	0.568
						0.597	0.295
						0.662	0.551
						0.659	0.552
						0.651	0.550
Genetic variation						0.793	0.691
						0.781	0.665
						0.737	0.464
						0.791	0.669
						0.796	0.687
						0.794	0.680
Gene expression						0.734	0.614
						0.720	0.620
						0.762	0.466
						0.733	0.612
						0.743	0.613
						0.735	0.612
Epigenetics						0.854	0.660
						0.833	0.660
						0.905	0.358
						0.857	0.679
						0.854	0.660
						0.854	0.660
Pharmacology						0.657	0.431
						0.626	0.442
						0.642	0.264
						0.643	0.419
						0.637	0.419
						0.647	0.433
Clinical marker						0.774	0.723
						0.767	0.728
						0.772	0.730
						0.768	0.678
						0.771	0.727
						0.772	0.719

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com