| Validating Automatic Measures | Cross Validation d_TUR d_QLT d_PAT Regular 0.176 0.155 0.151 Minus—one—model 0.224 0.180 0.178 |
| Validating Automatic Measures | Table 7: LOSS scores for Regular and Minus-one-model (during training) Cross Validations |
| Validating Automatic Measures | First, we use regular 4-fold cross validation where we randomly hold out 25% of the data for testing and train on the remaining 75% of the data for 4 rounds. |
| Experiments | The accuracy is measured by abstract-wise 10-fold cross validation and the one-answer-per-occurrence criterion (Giuliano et al., 2006). |
| Experiments | Table 3 shows the time for parsing the entire AImed corpus, and Table 4 shows the time required for 10-fold cross validation with GENIA-retrained parsers. |
| Experiments | Since we did not run experiments on protein-pair—wise cross validation , our system cannot be compared directly to the results reported by Erkan et al. |