Skip to main content

Table 6 The performance comparison of our method with baseline methods

From: A pattern learning-based method for temporal expression extraction and normalization from multi-lingual heterogeneous clinical texts

Language

Method

# exp.

# correct

Precision

Recall

F1

Chinese

GUTime

512

429

0.838

0.241

0.375

HeidelTime

954

824

0.864

0.463

0.603

CMedTEX

2293

1645

0.717

0.925

0.808

TEER_C

1761

1613

0.916

0.907

0.912

TEER

1761

1657

0.941

0.932

0.936

English

NLTK Timex

106

61

0.575

0.153

0.242

GUTime

101

88

0.871

0.221

0.353

IllinoisTExtractor

352

287

0.815

0.721

0.765

Heideltime

395

327

0.828

0.822

0.825

TEXer

360

340

0.944

0.854

0.897

TEER

368

349

0.948

0.877

0.911