Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,85 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- matthews_correlation
|
8 |
+
---
|
9 |
+
|
10 |
+
# sadickam/sdg-classification-bert
|
11 |
+
|
12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
13 |
+
|
14 |
+
This model is for classifying text with respect to the United Nations sustainable development goals (SDG).
|
15 |
+
|
16 |
+
|
17 |
+
## Model Details
|
18 |
+
|
19 |
+
### Model Description
|
20 |
+
|
21 |
+
<!-- Provide a longer summary of what this model is. -->
|
22 |
+
|
23 |
+
This text classification model was developed by fine-tuning the bert-base-uncased pre-trained model. The training data for this fine-tuned model was sourced from the publicly available OSDG Community Dataset (OSDG-CD) at https://zenodo.org/record/5550238#.ZBulfcJByF4.
|
24 |
+
This model was made as part of academic research at Deakin University. The goal was to make a transformer-based SDG text classification model that anyone could use. Only the first 16 UN SDGs supported. The primary model details are highlighted below:
|
25 |
+
|
26 |
+
- **Model type:** Text classification
|
27 |
+
- **Language(s) (NLP):** English
|
28 |
+
- **License:** mit
|
29 |
+
- **Finetuned from model [optional]:** bert-base-uncased
|
30 |
+
|
31 |
+
### Model Sources [optional]
|
32 |
+
<!-- Provide the basic links for the model. -->
|
33 |
+
- **Repository:** https://github.com/sadickam/sdg-classification-bert
|
34 |
+
- **Demo [optional]:** option 1: https://sadickam-sdg-text-classifier.hf.space/; option 2: https://sadickam-sdg-classification-bert-main-qxg1gv.streamlit.app/
|
35 |
+
|
36 |
+
|
37 |
+
### Direct Use
|
38 |
+
|
39 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
40 |
+
|
41 |
+
This is a fine-tuned model and therefore requires no further fine-tuning.
|
42 |
+
|
43 |
+
|
44 |
+
## How to Get Started with the Model
|
45 |
+
|
46 |
+
Use the code below to get started with the model.
|
47 |
+
```python
|
48 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
49 |
+
|
50 |
+
tokenizer = AutoTokenizer.from_pretrained("sadickam/sdg-classification-bert")
|
51 |
+
|
52 |
+
model = AutoModelForSequenceClassification.from_pretrained("sadickam/sdg-classification-bert")
|
53 |
+
```
|
54 |
+
|
55 |
+
|
56 |
+
## Training Data
|
57 |
+
|
58 |
+
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
59 |
+
The training data includes text from a wide range of industries and academic research fields. Hence, this fine-tuned model is not for a specific industry.
|
60 |
+
|
61 |
+
See training here: https://zenodo.org/record/5550238#.ZBulfcJByF4
|
62 |
+
|
63 |
+
|
64 |
+
## Training Hyperparameters
|
65 |
+
|
66 |
+
- Num_epoch = 3
|
67 |
+
- Learning rate = 5e-5
|
68 |
+
- Batch size = 16
|
69 |
+
|
70 |
+
|
71 |
+
## Evaluation
|
72 |
+
|
73 |
+
#### Metrics
|
74 |
+
|
75 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
76 |
+
- Accuracy = 0.9
|
77 |
+
- Matthews correlation = 0.89
|
78 |
+
|
79 |
+
|
80 |
+
<!--## Citation [optional] -->
|
81 |
+
|
82 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
83 |
+
|
84 |
+
|
85 |
+
<!--## Model Card Contact -->
|