Explore a thought-provoking 15-minute conference talk by Nicola Ferro and Mark Sanderson at SIGIR 2024, focusing on the dangers of uncontextualized significance in evaluation methodologies. Delve into the authors' insights on the importance of proper context when interpreting statistical significance in information retrieval research, and gain valuable perspectives on improving the reliability and validity of evaluation practices in the field.
Uncontextualized Significance Considered Dangerous in Evaluation - Session M1.5
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 M1.5 [fp] Uncontextualized significance considered dangerous
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
The Treatment of Ties in Rank-Biased Overlap - Evaluation M1.5
-
Dimension Importance Estimation for Dense Information Retrieval - Tutorial 2.1
-
A Reproducibility Study of PLAID - Neural IR
-
Can We Trust Recommender System Fairness Evaluation? The Role of Fairness and Relevance - Evaluation M1.5
-
What Matters in a Measure? A Perspective from Large-Scale Search Evaluation
-
Systematic Evaluation of Neural Retrieval Models on Touché 2020 Argument Retrieval Subset of BEIR
