|
--- |
|
license: mit |
|
language: |
|
- en |
|
metrics: |
|
- accuracy |
|
- mse |
|
- f1 |
|
base_model: |
|
- dmis-lab/biobert-base-cased-v1.2 |
|
- google-bert/bert-base-cased |
|
pipeline_tag: text-classification |
|
model-index: |
|
- name: bert-causation-rating-pubmed |
|
results: |
|
- task: |
|
type: text-classification |
|
dataset: |
|
name: pubmed_textdata |
|
type: dataset |
|
metrics: |
|
- name: off by 1 accuracy |
|
type: accuracy |
|
value: 83.5621 |
|
- name: mean squared error for ordinal data |
|
type: mse |
|
value: 0.8108 |
|
- name: weighted F1 score |
|
type: f1 |
|
value: 0.8208 |
|
- name: Kendall's tau coefficient |
|
type: Kendall's tau |
|
value: 0.7929 |
|
|
|
--- |
|
|
|
# Model |
|
This is a BioBERT based model trained on a set of manually annotated texts with causation labels, tasked with classifying a sentence into different levels of strength of causation. |
|
This `rating-pubmed` version is tuned on the dataset provided in a published article [Yu et al. (2019)](https://aclanthology.org/D19-1473/) *Detecting Causal Language Use in Science Findings*. |
