metadata

language: en
license: apache-2.0
tags:
  - metaphor-detection
  - bert
  - text-classification
  - nlp
  - transformer
model-index:
  - name: Fine-Tuned Metaphor Detection Model
    results:
      - task:
          name: text-classification
          type: text-classification
        metrics:
          - name: Accuracy
            value: 72
            type: accuracy
metrics:
  - accuracy
base_model:
  - Sasidhar1826/common_metaphors_detection
pipeline_tag: text-classification
datasets:
  - Sasidhar1826/manual_data_on_metaphors

Fine-Tuned Metaphor Detection Model

This is the extention of my previously trained model.

This is a fine-tuned version of a BERT-based model used for metaphor detection in text. The model was trained on a custom dataset with sentences labeled as either metaphors or literals.

Model Details

Model architecture: BERT-based model
Number of labels: 2 (Metaphor, Literal)
Training epochs: 1
Batch size: 8
Learning rate: 1e-5
Evaluation metric: Accuracy
Accuracy: 72%

How to use

You can use this model to predict whether a sentence contains a metaphor or not. Below is an example of how to load the model and use it for inference:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("your-username/fine-tuned-metaphor-detection")
model = AutoModelForSequenceClassification.from_pretrained("your-username/fine-tuned-metaphor-detection")

# Example text
text = "Time is a thief."

# Tokenize input and get predictions
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
with torch.no_grad():
    outputs = model(**inputs)
    logits = outputs.logits
    prediction = torch.argmax(logits, dim=-1)

print("Prediction:", "Metaphor" if prediction.item() == 1 else "Literal")