Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ widget:
|
|
13 |
A fine-tuned model for fact-classification task on English tweets about COVID-19/vaccine.
|
14 |
|
15 |
## Intended uses & limitations
|
16 |
-
You can classify if the input tweet (or any others statement) about COVID-19/vaccine is true
|
17 |
Note that since this model was trained with data up to May 2020, the most recent information may not be reflected.
|
18 |
|
19 |
#### How to use
|
@@ -45,14 +45,14 @@ pipe(seq)
|
|
45 |
]
|
46 |
```
|
47 |
|
48 |
-
-
|
49 |
```python
|
50 |
"By the end of 2020, several vaccines had become available for use in different parts of the world."
|
51 |
"Vaccines to prevent SARS-CoV-2 infection are considered the most promising approach for curbing the pandemic."
|
52 |
"RNA vaccines were the first vaccines for SARS-CoV-2 to be produced and represent an entirely new vaccine approach."
|
53 |
```
|
54 |
|
55 |
-
-
|
56 |
```python
|
57 |
"COVID-19 vaccine caused new strain in UK."
|
58 |
```
|
@@ -82,9 +82,9 @@ To conservatively classify whether an input sequence is true or not, the model m
|
|
82 |
- A fine-tuned model from pre-trained language model (1) for fact-classification task on COVID-19/vaccine.
|
83 |
- COVID-19/vaccine-related statements were collected from [Poynter](https://www.poynter.org/ifcn-covid-19-misinformation/) and [Snopes](https://www.snopes.com/) using Selenium resulting in over 14,000 fact-checked statements from Jan 2020 to May 2021.
|
84 |
- Original labels were divided within following three categories:
|
85 |
-
- `False`: includes false, no evidence, manipulated, fake, not true, unproven
|
86 |
-
- `Misleading`: includes misleading, exaggerated, out of context
|
87 |
-
- `True`: includes true
|
88 |
|
89 |
## Evaluation results
|
90 |
| Training loss | Validation loss | Training accuracy | Validation accuracy |
|
|
|
13 |
A fine-tuned model for fact-classification task on English tweets about COVID-19/vaccine.
|
14 |
|
15 |
## Intended uses & limitations
|
16 |
+
You can classify if the input tweet (or any others statement) about COVID-19/vaccine is `true`, `false` or `misleading`.
|
17 |
Note that since this model was trained with data up to May 2020, the most recent information may not be reflected.
|
18 |
|
19 |
#### How to use
|
|
|
45 |
]
|
46 |
```
|
47 |
|
48 |
+
- `true` examples
|
49 |
```python
|
50 |
"By the end of 2020, several vaccines had become available for use in different parts of the world."
|
51 |
"Vaccines to prevent SARS-CoV-2 infection are considered the most promising approach for curbing the pandemic."
|
52 |
"RNA vaccines were the first vaccines for SARS-CoV-2 to be produced and represent an entirely new vaccine approach."
|
53 |
```
|
54 |
|
55 |
+
- `false` examples
|
56 |
```python
|
57 |
"COVID-19 vaccine caused new strain in UK."
|
58 |
```
|
|
|
82 |
- A fine-tuned model from pre-trained language model (1) for fact-classification task on COVID-19/vaccine.
|
83 |
- COVID-19/vaccine-related statements were collected from [Poynter](https://www.poynter.org/ifcn-covid-19-misinformation/) and [Snopes](https://www.snopes.com/) using Selenium resulting in over 14,000 fact-checked statements from Jan 2020 to May 2021.
|
84 |
- Original labels were divided within following three categories:
|
85 |
+
- `False`: includes false, no evidence, manipulated, fake, not true, unproven and unverified
|
86 |
+
- `Misleading`: includes misleading, exaggerated, out of context and needs context
|
87 |
+
- `True`: includes true and correct
|
88 |
|
89 |
## Evaluation results
|
90 |
| Training loss | Validation loss | Training accuracy | Validation accuracy |
|