Skip to main content

Table 3 Evaluation results for the PMC15 data set.

From: Building a protein name dictionary from full text: a machine learning term extraction approach

Evaluation

Performance Measure

YAGI

Textractor

NLProt

micro-evaluation

precision

43%

66%

34%

micro-evaluation

rel. recall

63%

31%

41%

micro-evaluation

rel F-1

51%

42%

37%

macro-evaluation

precision

40%

53%

29%

macro-evaluation

rel. recall

66%

30%

37%

macro-evaluation

rel F-1

52%

40%

34%