BERT Topic Classification

Training Data

This model was fine-tuned on the AG News dataset (fancyzhx/ag_news) for four-class news topic classification:

World
Sports
Business
Sci/Tech

The dataset was divided into 108,000 training examples, 12,000 validation examples, and 7,600 test examples. A random seed of 42 was used.

Metrics

Test-set results:

Metric	Score
Accuracy	94.49%
Macro F1	94.49%
Loss	0.3470

Intended Use

This model is intended for English news topic classification into the four AG News categories: World, Sports, Business, and Sci/Tech.

It was developed for educational purposes and experimentation with BERT adaptation methods.

Example Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_id = "karencardiel/topic-classification-bert"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)

text = "Researchers developed a new artificial intelligence system for analyzing genomic data."

inputs = tokenizer(
    text,
    return_tensors="pt",
    truncation=True,
    padding=True
)

with torch.no_grad():
    outputs = model(**inputs)

prediction = torch.argmax(outputs.logits, dim=1).item()
label = model.config.id2label[prediction]

print("Predicted topic:", label)

Example output:

Predicted topic: Sci/Tech

Limitations

The model is trained on English news data and may not generalize well to other domains or languages.
It only supports the four categories present in AG News.
Performance on real-world data may differ from the reported test-set results.
The model is not intended for high-stakes decision-making.

References

Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. https://arxiv.org/abs/1810.04805

Zhang, X., Zhao, J., & LeCun, Y. (2015). Character-level Convolutional Networks for Text Classification. https://arxiv.org/abs/1509.01626

Tunstall, L., von Werra, L., & Wolf, T. Natural Language Processing with Transformers. O'Reilly Media, Chapter 2.