---
license: mit
widget:
- text: "whaling is part of the culture of various indigenous population and should be allowed for the purpose of maintaining this tradition and way of life and sustenance, among other uses of a whale. against We should ban whaling"
---
This is a fine-tuned Deberta model to detect human values in arguments. 
The model is part of the ensemble that was the best-performing system in the SemEval2023 task: [Detecting Human Values in arguments](https://touche.webis.de/semeval23/touche23-web/index.html)
It was trained and tested on a dataset of 9324 annotated [arguments](https://zenodo.org/record/7550385#.ZEPzcfzP330). 
The whole ensemble system achieved a F1-Score of 0.56 in the competiton. This model achieves a F1-Score of 0.55. 

## Model Usage

This model is built on custom code. So the inference api cannot be used directly.
To use the model please follow the steps below... 


```python

from transformers import AutoModelForSequenceClassification, AutoTokenizer

tokenizer =  AutoTokenizer.from_pretrained("tum-nlp/Deberta_Human_Value_Detector")
trained_model = AutoModelForSequenceClassification.from_pretrained("tum-nlp/Deberta_Human_Value_Detector", trust_remote_code=True)

example_text ='whaling is part of the culture of various indigenous population and should be allowed for the purpose of maintaining this tradition and way of life and sustenance, among other uses of a whale. against We should ban whaling'

encoding = tokenizer.encode_plus(
        example_text,
        add_special_tokens=True,
        max_length=512,
        return_token_type_ids=False,
        padding="max_length",
        return_attention_mask=True,
        return_tensors='pt',
    )

with torch.no_grad():
        test_prediction = trained_model(encoding["input_ids"], encoding["attention_mask"])
        test_prediction = test_prediction["output"].flatten().numpy()

```

## Prediction
To make a prediction and map the the outputs to the correct labels.
During the competiton a threshold of 0.25 was used to binarize the output. 
```python
THRESHOLD = 0.25
LABEL_COLUMNS = ['Self-direction: thought','Self-direction: action','Stimulation','Hedonism','Achievement','Power: dominance','Power: resources','Face','Security: personal',
                 'Security: societal','Tradition','Conformity: rules','Conformity: interpersonal','Humility','Benevolence: caring','Benevolence: dependability','Universalism: concern','Universalism: nature','Universalism: tolerance','Universalism: objectivity']
print(f"Predictions:")
for label, prediction in zip(LABEL_COLUMNS, test_prediction):
    if prediction < THRESHOLD:
        continue
    print(f"{label}: {prediction}")
```