DataHour: Bias and Fairness in NLP

DataHour: Bias and Fairness in NLP

25 Jul 202213:07pm - 25 Jul 202214:07pm

DataHour: Bias and Fairness in NLP

About the Event

Biases are stereotypical/unjust associations a model encodes with respect to protected attributes, or subpar model performance for certain groups. Hence, bias mitigation is the process of lessening the severity of stereotypical/unjust associations and disparate model performance.

Fairness concerns ensuring that a model performs equitably for all groups of people with respect to protected attributes. 

This DataHour will cover the background of how biases can occur in NLP systems and why it is important to identify them. The session will also include techniques to identify and mitigate these biases and how fairness can be estimated. The discussion will revolve mostly around "algorithmic bias" that is, the "unjust, unfair, or prejudicial treatment of people related to race, income, sexual orientation, religion, gender, and other characteristics historically associated with discrimination and marginalization, when and where they manifest in algorithmic systems or algorithmically aided decision-making".

Prerequisites: Enthusiasm for learning Data Science and familiarity with ML and NLP.

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space
  4. Best articles get published on Analytics Vidhya’s Blog Space
  5. Best articles get published on Analytics Vidhya’s Blog Space

Who is this DataHour for?

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space

About the Speaker

Shantam Saxena

Shantam Saxena

Data Scientist at McKinsey & Company

Shantam currently works at Mckinsey and Company and has an experience of more than 5 years and works mostly around NLP and related problems.  He is currently pursuing Masters in AI from IIT Jodhpur and will be starting his research on graph neural networks. Shantam likes to write poems whenever he gets time and is currently exploring the realm of photography, mainly street style.You can follow him on Linkedin.

Participate in discussion

Registration Details

10525

Registered

Become a Speaker

Share your vision, inspire change, and leave a mark on the industry. We're calling for innovators and thought leaders to speak at our event

  • Professional Exposure
  • Networking Opportunities
  • Thought Leadership
  • Knowledge Exchange
  • Leading-Edge Insights
  • Community Contribution