lcampillos
commited on
Commit
•
c2b894b
1
Parent(s):
fcab806
Update README.md
Browse files
README.md
CHANGED
@@ -30,10 +30,10 @@ This named entity recognition model detects temporal expressions (TIMEX) accordi
|
|
30 |
- Time: e.g. *noche*
|
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.
|
34 |
-
- Recall: 0.
|
35 |
-
- F1: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -95,25 +95,27 @@ The following hyperparameters were used during training:
|
|
95 |
- seed: we used different seeds for 5 evaluation rounds, and uploaded the model with the best results
|
96 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
97 |
- lr_scheduler_type: linear
|
98 |
-
- num_epochs:
|
99 |
|
100 |
|
101 |
### Training results (test set; average and standard deviation of 5 rounds with different seeds)
|
102 |
|
103 |
| Precision | Recall | F1 | Accuracy |
|
104 |
|:--------------:|:--------------:|:--------------:|:--------------:|
|
105 |
-
| 0.
|
106 |
|
107 |
|
108 |
**Results per class (test set; average and standard deviation of 5 rounds with different seeds)**
|
109 |
|
|
|
110 |
| Class | Precision | Recall | F1 | Support |
|
111 |
|:---------:|:--------------:|:--------------:|:--------------:|:---------:|
|
112 |
-
| Age | 0.
|
113 |
-
| Date | 0.931 (±0.
|
114 |
-
| Duration | 0.
|
115 |
-
| Frequency | 0.
|
116 |
-
| Time | 0.
|
|
|
117 |
|
118 |
|
119 |
### Framework versions
|
|
|
30 |
- Time: e.g. *noche*
|
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: 0.900 (±0.011)
|
34 |
+
- Recall: 0.900 (±0.009)
|
35 |
+
- F1: 0.900 (±0.007)
|
36 |
+
- Accuracy: 0.996 (±0.001)
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
95 |
- seed: we used different seeds for 5 evaluation rounds, and uploaded the model with the best results
|
96 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
97 |
- lr_scheduler_type: linear
|
98 |
+
- num_epochs: average of 14 epochs (±2.24)
|
99 |
|
100 |
|
101 |
### Training results (test set; average and standard deviation of 5 rounds with different seeds)
|
102 |
|
103 |
| Precision | Recall | F1 | Accuracy |
|
104 |
|:--------------:|:--------------:|:--------------:|:--------------:|
|
105 |
+
| 0.900 (±0.011) | 0.900 (±0.009) | 0.900 (±0.007) | 0.996 (±0.001) |
|
106 |
|
107 |
|
108 |
**Results per class (test set; average and standard deviation of 5 rounds with different seeds)**
|
109 |
|
110 |
+
|:---------:|:--------------:|:--------------:|:--------------:|:---------:|
|
111 |
| Class | Precision | Recall | F1 | Support |
|
112 |
|:---------:|:--------------:|:--------------:|:--------------:|:---------:|
|
113 |
+
| Age | 0.926 (±0.013) | 0.947 (±0.009) | 0.936 (±0.010) | 372 |
|
114 |
+
| Date | 0.931 (±0.015) | 0.895 (±0.014) | 0.913 (±0.013) | 412 |
|
115 |
+
| Duration | 0.918 (±0.014) | 0.893 (±0.019) | 0.905 (±0.010) | 629 |
|
116 |
+
| Frequency | 0.780 (±0.043) | 0.885 (±0.008) | 0.829 (±0.024) | 73 |
|
117 |
+
| Time | 0.722 (±0.068) | 0.809 (±0.042) | 0.762 (±0.052) | 113 |
|
118 |
+
|
119 |
|
120 |
|
121 |
### Framework versions
|