Table 4 Composition of the training sets
From: Building a protein name dictionary from full text: a machine learning term extraction approach
Training lists | PG | C | IK | Pr |
|---|---|---|---|---|
# n-grams, n>=2 | 304 | 193 | 111 | 254 |
# occurrences in articles where the n-gram is most frequent | 16,543 | 10,862 | 5,853 | 12,547 |