Modelpublic

claritylab/zero-shot-explicit-binary-bert

sourceHugging Facemitupdated 3y agoView on Hugging Face

1likes42downloads

Model Card

Zero-shot Explicit Binary BERT

This is a BERT model. It was introduced in the Findings of ACL'23 Paper Label Agnostic Pre-training for Zero-shot Text Classification by *Christopher Clarke, Yuzhao Heng, Yiping Kang, Krisztian Flautner, Lingjia Tang and Jason Mars*. The code for training and evaluating this model can be found here.

Model description

This model is intended for zero-shot text classification. It was trained under the binary classification framework via explicit training with the aspect-normalized UTCD dataset.

—Finetuned from model: `bert-base-uncased`

Usage

Install our python package:

bash

pip install zeroshot-classifier

Then, you can use the model like this:

python

>>> from zeroshot_classifier.models import BinaryBertCrossEncoder
>>> model = BinaryBertCrossEncoder(model_name='claritylab/zero-shot-explicit-binary-bert')

>>> text = "I'd like to have this track onto my Classical Relaxations playlist."
>>> labels = [
>>>     'Add To Playlist', 'Book Restaurant', 'Get Weather', 'Play Music', 'Rate Book', 'Search Creative Work',
>>>     'Search Screening Event'
>>> ]

>>> query = [[text, lb] for lb in labels]
>>> logits = model.predict(query, apply_softmax=True)
>>> print(logits)

[[1.0987393e-03 9.9890125e-01]
 [9.9988937e-01 1.1059999e-04]
 [9.9986207e-01 1.3791372e-04]
 [1.6576477e-03 9.9834239e-01]
 [9.9990320e-01 9.6742726e-05]
 [9.9894422e-01 1.0557596e-03]
 [9.9959773e-01 4.0229000e-04]]