Research Article
ChemTok: A New Rule Based Tokenizer for Chemical Named Entity Recognition
Table 6
NER performance (
-score in %) of classifiers using BioCreative data set.
| Tokenizer | Classification algorithm | CRF | SVM | Development | Test | Development | Test |
| White space | 75.39 | 75.44 | 75.65 | 75.67 | ChemSpot | 78.46 | 78.89 | 83.26 | 82.88 | tmVar | 76.15 | 76.50 | 82.29 | 82.27 | ChemTok | 81.77 | 81.89 | 85.15 | 84.94 |
|
|