Reading Between the Lines - The Hidden Bias of NLP - Dr Dirk Hovy
Offered By: Alan Turing Institute via YouTube
Course Description
Overview
Explore the hidden biases in Natural Language Processing (NLP) with Dr. Dirk Hovy in this 33-minute conference talk from the Alan Turing Institute's workshop on "Bridging disciplines in analysing text as social and cultural data." Delve into the methodological challenges that cut across research disciplines, examining various types of biases including selection bias, annotation bias, model bias, and design bias. Learn about the MACE (Multi-Annotator Competence Estimation) approach and its implications for NLP. Discover how American English influences NLP models and consider strategies for moving forward in addressing these biases. Gain insights into the interdisciplinary synergies required to tackle the complex issues at the intersection of NLP, machine learning, humanities, and social sciences.
Syllabus
Alan Turing
Selection Bias
Annotation Bias
MACE
Model Bias
Design Bias
American English
Moving Forward
Questions?
Taught by
Alan Turing Institute
Related Courses
Know Thyself - The Value and Limits of Self-Knowledge: The Examined LifeUniversity of Edinburgh via Coursera Latin American Culture
Tecnológico de Monterrey via Coursera Introduction to Box'Tag
OpenLearning Science, Technology, and Society in China II: History of S&T in Chinese Society
The Hong Kong University of Science and Technology via Coursera Science, Technology, and Society in China III: The Present & Policy Implications
The Hong Kong University of Science and Technology via Coursera