metadata
language:
- en
tags:
- Text Classification
co2_eq_emissions: 0.319355 Kg
widget:
- text: >-
Nevertheless, Trump and other Republicans have tarred the protests as
havens for terrorists intent on destroying property.
example_title: Biased example 1
- text: >-
Christians should make clear that the perpetuation of objectionable
vaccines and the lack of alternatives is a kind of coercion.
example_title: Biased example 2
- text: >-
But it was Hawley’s keynote address at the National Conservatism
Conference that nailed down who he is, what he believes, and where his
party is going in a way that should be absolutely terrifying for every
American.
example_title: Non-Biased example 1
- text: >-
While emphasizing he’s not singling out either party, Cohen warned about
the danger of normalizing white supremacist ideology.
example_title: Non-Biased example 2
About the Model
An English Classification model, trained on MBAD Dataset to detect bias and fairness in sentences.
- Dataset : MBAD Data
- Carbon emission 0.319355 Kg
| Train Accuracy | Validation Accuracy | Train loss | Test loss |
|---|---|---|---|
| 76.97 | 62.00 | 0.45 | 0.96 |
Usage
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("dreji18/bias-detection-model", use_auth_token=True)
model = TFAutoModelForSequenceClassification.from_pretrained("dreji18/bias-detection-model", use_auth_token=True)
classifier = pipeline('text-classification', model=model, tokenizer=tokenizer) # cuda = 0,1 based on gpu availability
classifier("While emphasizing he’s not singling out either party, Cohen warned about the danger of normalizing white supremacist ideology.")
Author
This model is part of the Research topic "Bias and Fairness in AI" conducted by Shaina Raza, Deepak John Reji, Chen Ding. If you use this work (code, model or dataset), please cite as:
Bias & Fairness in AI, (2020), GitHub repository, https://github.com/dreji18/Fairness-in-AI/tree/dev