ARTICLEBias in Machine learning models

Covers: theory of Bias
Estimated time needed: 10 minutes
Questions this item adddesses:
  • What is bias and sources of bias in ML models?
How to use this item?

Read full medium artcile.

URL: https://towardsdatascience.com/ai-policy-making-part-4-a-primer-on-fair-and-responsible-ml-and-ai-28f52b32190f
Author(s) / creator(s) / reference(s)
refer to the link
Shortlist
publicShare

Algorithmic bias and fairness in Natural Language Processing

Sharvari DhoteTotal time needed: ~3 hours
Learning Objectives
Introduction to bias and fairness in Natural language processing
Potential Use Cases
It is very important to learn and understand harms in machine learning model to develop responsible and fair models.
Target Audience
INTERMEDIATENLP Data scientist from all audience levels
Go through the following annotated items in order:
ARTICLE 1. AI Ethics Primer
  • What is AI ethics ?
30 minutes
ARTICLE 2. Bias in Machine learning models
  • What is bias and sources of bias in ML models?
10 minutes
ARTICLE 3. Fairness definitions
  • What is fairness and various fairness definitions?
30 minutes
OTHER 4. Type of biases and evaluating fairness in Natural Language Processing (NLP)
  • What is bias and fairness in Natural language processing?
  • What are the type of harms in NLP model?
  • How bias is generated in NLP?
30 minutes
ARTICLE 5. Algorithmic Bias in Natural language processing models
  • What are type of biases and algorithmic bias?
30 minutes

Concepts Convered