dell-research-harvard/topic-fire

Fine-tuned distilroberta-base for detecting news on fires

Model Description

This model is a finetuned distilroberta-base, for classifying whether news articles are about fires.

How to Use

from transformers import pipeline
classifier = pipeline("text-classification", model="dell-research-harvard/topic-fire")
classifier("Building destroyed by fire")

Training data

The model was trained on a hand-labelled sample of data from the NEWSWIRE dataset.

Split	Size
Train	554
Dev	118
Test	118

Test set results

Metric	Result
F1	0.9709
Accuracy	0.9746
Precision	0.9434
Recall	1.0000

Citation Information

You can cite this dataset using

@misc{silcock2024newswirelargescalestructureddatabase,
      title={Newswire: A Large-Scale Structured Database of a Century of Historical News}, 
      author={Emily Silcock and Abhishek Arora and Luca D'Amico-Wong and Melissa Dell},
      year={2024},
      eprint={2406.09490},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2406.09490}, 
}

Applications

We applied this model to a century of historical news articles. You can see all the classifications in the NEWSWIRE dataset.