AI & ML interests

BEIR (Benchmarking IR) consists of a homogenous benchmark for diverse sentence or passage level IR tasks. It provides a common and easy framework for the cross-domain evaluation of your retrieval models.

Recent Activity

nthakur 
in BeIR/scifact 3 months ago
nthakur 
in BeIR/fever 3 months ago
nthakur 
in BeIR/scidocs 3 months ago
nthakur 
in BeIR/quora 3 months ago