Skip to main content

Advertisement

Table 8 Estimated recalls for Linguistic Patterns 1, 2 and 3

From: Identifying named entities from PubMed® for enriching semantic categories

Headwords Pattern 1 Pattern 2 Pattern 3 Total
Gene 13.5% 0.6% 2.4% 14.0%
Protein 8.7% 1.6% 3.9% 10.6%
Disease 0.5% 0.4% 4.5% 4.8%
Cell 0.7% 0.5% 2.1% 2.4%
Cells 1.8% 0.9% 1.3% 2.8%
Average 5.0% 0.8% 2.8% 6.9%
  1. As no true labels are available for PubMed terms, recalls were evaluated based on number of SemCat terms occurring in PubMed that were discovered by the pattern.