distilBART-mnli-cnn_news

distilBART-MNLI for ZeroShot-Text-Classification fine tuned on cnn news article

This is a Huggingface model fine-tuned on the CNN news dataset for zero-shot text classification task using DistilBART-MNLI. The model achieved an f1 score of 93% and an accuracy of 93% on the CNN test dataset with a maximum length of 128 tokens.

Authors

This work was done by CHERGUELAINE Ayoub & BOUBEKRI Faycal

Original Model

valhalla/distilbart-mnli-12-1

Model Architecture

The model architecture is based on the DistilBART-MNLI transformer model. DistilBART is a smaller and faster version of BART that is pre-trained on a large corpus of text and fine-tuned on downstream natural language processing tasks.

Dataset

The CNN news dataset was used for fine-tuning the model. This dataset contains news articles from the CNN website and is labeled into 6 categories, including politics, health, entertainment, tech, travel, world, and sports.

Fine-tuning Parameters

The model was fine-tuned for 1 epoch on a maximum length of 256 tokens. The training took approximately 6 hours to complete.

Evaluation Metrics

The model achieved an f1 score of 93% and an accuracy of 93% on the CNN test dataset with a maximum length of 128 tokens.

Usage

The model can be used for zero-shot text classification tasks on news articles. It can be accessed via the Huggingface Transformers library using the following code:

from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("AyoubChLin/DistilBart_cnn_zeroShot")

model = AutoModelForSequenceClassification.from_pretrained("AyoubChLin/DistilBart_cnn_zeroShot")
classifier = pipeline(
    "zero-shot-classification",
    model=model,
    tokenizer=tokenizer,
    device=0
)

Acknowledgments

We would like to acknowledge the Huggingface team for their open-source implementation of transformer models and the CNN news dataset for providing the labeled dataset for fine-tuning.