dell-research-harvard/wire-classifier

Fine-tuned distilroberta-base for detecting whether news is from a wire service

Model Description

This model is a finetuned distilroberta-base, for classifying whether news articles are from a wire service.

How to Use

from transformers import pipeline
classifier = pipeline("text-classification", model="dell-research-harvard/wire-classifier")
classifier("Washington (AP) Two men died in a car crash")

Training data

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

Split	Size
Train	1,459
Dev	336
Test	448

Test set results

Metric	Result
F1	0.96
Accuracy
Precision
Recall

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.