lcampillos commited on
Commit
a0c23f2
1 Parent(s): fedc38c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -30,10 +30,10 @@ This named entity recognition model detects negation and speculation entities, a
30
  - Speculated: speculated entity or event (e.g. *posiblemente **sobreviva***)
31
 
32
  The model achieves the following results on the test set (when trained with the training and development set; results are averaged over 5 evaluation rounds):
33
- - Precision: 0.833 (±0.001)
34
- - Recall: 0.870 (±0.001)
35
- - F1: 0.851 (±0.001)
36
- - Accuracy: 0.956 (±0.001)
37
 
38
  ## Model description
39
 
@@ -100,24 +100,24 @@ The following hyperparameters were used during training:
100
  - seed: we used different seeds for 5 evaluation rounds, and uploaded the model with the best results
101
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
102
  - lr_scheduler_type: linear
103
- - num_epochs: 4
104
 
105
 
106
  ### Training results (test set; average and standard deviation of 5 rounds with different seeds)
107
 
108
  | Precision | Recall | F1 | Accuracy |
109
  |:--------------:|:--------------:|:--------------:|:--------------:|
110
- | 0.833 (±0.001) | 0.870 (±0.001) | 0.851 (±0.001) | 0.986 (±0.001) |
111
 
112
 
113
  **Results per class (test set; average and standard deviation of 5 rounds with different seeds)**
114
 
115
  | Class | Precision | Recall | F1 | Support |
116
  |:-----------:|:--------------:|:--------------:|:--------------:|:---------:|
117
- | Neg_cue | 0.944 (±0.001) | 0.963 (±0.002) | 0.954 (±0.001) | 2416 |
118
- | Negated | 0.805 (±0.003) | 0.843 (±0.005) | 0.823 (±0.003) | 3064 |
119
- | Spec_cue | 0.800 (±0.005) | 0.862 (±0.006) | 0.830 (±0.002) | 746 |
120
- | Speculated | 0.683 (±0.009) | 0.735 (±0.010) | 0.708 (±0.009) | 993 |
121
 
122
 
123
  ### Framework versions
 
30
  - Speculated: speculated entity or event (e.g. *posiblemente **sobreviva***)
31
 
32
  The model achieves the following results on the test set (when trained with the training and development set; results are averaged over 5 evaluation rounds):
33
+ - Precision: 0.838 (±0.003)
34
+ - Recall: 0.866 (±0.005)
35
+ - F1: 0.852 (±0.003)
36
+ - Accuracy: 0.986 (±0.001)
37
 
38
  ## Model description
39
 
 
100
  - seed: we used different seeds for 5 evaluation rounds, and uploaded the model with the best results
101
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
102
  - lr_scheduler_type: linear
103
+ - num_epochs: 8
104
 
105
 
106
  ### Training results (test set; average and standard deviation of 5 rounds with different seeds)
107
 
108
  | Precision | Recall | F1 | Accuracy |
109
  |:--------------:|:--------------:|:--------------:|:--------------:|
110
+ | 0.838 (±0.003) | 0.866 (±0.005) | 0.852 (±0.003) | 0.986 (±0.001) |
111
 
112
 
113
  **Results per class (test set; average and standard deviation of 5 rounds with different seeds)**
114
 
115
  | Class | Precision | Recall | F1 | Support |
116
  |:-----------:|:--------------:|:--------------:|:--------------:|:---------:|
117
+ | Neg_cue | 0.945 (±0.004) | 0.961 (±0.002) | 0.953 (±0.003) | 2416 |
118
+ | Negated | 0.815 (±0.003) | 0.838 (±0.005) | 0.826 (±0.003) | 3064 |
119
+ | Spec_cue | 0.811 (±0.005) | 0.868 (±0.009) | 0.839 (±0.005) | 746 |
120
+ | Speculated | 0.685 (±0.009) | 0.719 (±0.016) | 0.701 (±0.008) | 993 |
121
 
122
 
123
  ### Framework versions