kelingwang
commited on
Commit
•
9d49652
1
Parent(s):
e3e6403
Update README.md
Browse files
README.md
CHANGED
@@ -40,7 +40,7 @@ datasets:
|
|
40 |
|
41 |
# Model description
|
42 |
This `bert-causation-rating-dr1` model is a fine-tuned [biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) model on a small set of manually annotated texts with causation labels. This model is tasked with classifying a sentence into different levels of strength of causation expressed in this sentence.
|
43 |
-
|
44 |
The sentences in the dataset were rated independently by two researchers. This `dr1` version is tuned on the set of sentences with labels rated by Rater 1.
|
45 |
|
46 |
# Intended use and limitations
|
@@ -56,7 +56,7 @@ This model predicts strength of causation (SoC) labels based on the text inputs
|
|
56 |
|
57 |
# Performance and hyperparameters
|
58 |
## Test metrics
|
59 |
-
This model achieves the following results on the test dataset. The test dataset is a 25% held-out split of the entire dataset with `SEED=114514`.
|
60 |
* Loss: 0.5916
|
61 |
* Off-by-1 accuracy: 88.1356
|
62 |
* Off-by-2 accuracy: 100.0000
|
@@ -78,6 +78,7 @@ During the Bayesian optimization procedure for hyperparameter tuning, this model
|
|
78 |
# Training settings
|
79 |
|
80 |
The following training configurations apply:
|
|
|
81 |
* `seed`: 114514
|
82 |
* `batch_size`: 128
|
83 |
* `epoch`: 8
|
|
|
40 |
|
41 |
# Model description
|
42 |
This `bert-causation-rating-dr1` model is a fine-tuned [biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) model on a small set of manually annotated texts with causation labels. This model is tasked with classifying a sentence into different levels of strength of causation expressed in this sentence.
|
43 |
+
Before tuning on this dataset, the `biobert-base-cased-v1.2` model is fine-tuned on a dataset containing causation labels from a published paper. This model starts from pre-trained [`kelingwang/bert-causation-rating-pubmed`](https://huggingface.co/kelingwang/bert-causation-rating-pubmed). For more information please view the link and my [GitHub page](https://github.com/Keling-Wang/causation_rating).
|
44 |
The sentences in the dataset were rated independently by two researchers. This `dr1` version is tuned on the set of sentences with labels rated by Rater 1.
|
45 |
|
46 |
# Intended use and limitations
|
|
|
56 |
|
57 |
# Performance and hyperparameters
|
58 |
## Test metrics
|
59 |
+
This model achieves the following results on the test dataset. The test dataset is a 25% held-out stratified split of the entire dataset with `SEED=114514`.
|
60 |
* Loss: 0.5916
|
61 |
* Off-by-1 accuracy: 88.1356
|
62 |
* Off-by-2 accuracy: 100.0000
|
|
|
78 |
# Training settings
|
79 |
|
80 |
The following training configurations apply:
|
81 |
+
* Pre-trained model: `kelingwang/bert-causation-rating-pubmed`
|
82 |
* `seed`: 114514
|
83 |
* `batch_size`: 128
|
84 |
* `epoch`: 8
|