NLM IRP Seminar Schedule
UPCOMING SEMINARS
RECENT SEMINARS
-
July 23, 2024 Yu group
Yu Group Research Update -
July 18, 2024 Xiaofang Jiang
Jiang Lab research updates -
May 30, 2024 Deepak Gupta
Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches -
May 28, 2024 Harutyun Saakyan
Simulation of protein fold evolution with atomistic details -
May 23, 2024 Leslie Ronish
Identification of fold-switching proteins by FLIM-FRET
Scheduled Seminars on Oct. 31, 2023
Contact NLM_IRP_Seminar_Scheduling@mail.nih.gov with questions about this seminar.
Abstract:
Along with the dramatic growth of interest in artificial intelligence and deep learning is a growth in questions about such algorithms. For example, are they fair? A machine learning algorithm is behind PubMed search's Best Match algorithm. NIST's AI Risk Management Framework points out that fairness needs to be regularly measured and tracked across changes in algorithms. We measured fairness in PubMed search in the areas of article language and journal ranking. We also modified the search algorithm by changing which clicks are used to score articles and adding a dense retrieval feature. We measure the effect on fairness resulting from these changes. We conclude with a discussion of the implementation and implications of a common suggestion for balancing fairness and relevance of search results.