uvegesistvan/EGD_distilbert-base-multilingual-cased

EGD DistilBERT (Multilingual Cased)

Model Overview

This model is based on DistilBERT-base-multilingual-cased and has been fine-tuned on English, Hungarian, and German data for text classification of European Parliamentary speeches into rhetorical categories.

The model classifies text into three categories:

• 0 - Other (text that does not fit into moralist or realist categories)
• 1 - Moralist (arguments emphasizing moral reasoning)
• 2 - Realist (arguments applying pragmatic or realist reasoning)

This model is useful for analyzing political discourse and rhetorical styles in multiple languages.

---

Evaluation Results

The model was evaluated on a test set of 938 sentences, with the following results:

Label	Precision	Recall	F1-score	Support
0 - Other	0.91	0.92	0.92	783
1 - Moralist	0.49	0.40	0.44	65
2 - Realist	0.43	0.44	0.44	90

• Overall accuracy: 0.84
• Macro average F1-score: 0.60
• Weighted average F1-score: 0.84

The model reliably distinguishes the general (other) class from moralist and realist arguments, though performance on the minority classes (1 and 2) is lower.

---

Usage

This model can be used with the Hugging Face Transformers library:

from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_name = "uvegesistvan/EGD_distilbert-base-multilingual-cased"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Classify an example text
text = "The European Union has a responsibility towards future generations."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits

# Get predicted class
predicted_class = logits.argmax().item()
print(f"Predicted class: {predicted_class}")