← Search

Sergii Kashubin

1 accepted papers

2020

Measuring Compositional Generalization: A Comprehensive Method on Realistic Data

ICLR 2020poster

State-of-the-art machine learning methods exhibit limited compositional generalization. At the same time, there is a lack of realistic benchmarks that comprehensively measure this ability, which makes it challenging to find and evaluate improvements. We introduce a novel method to systematically con…

Cited by 406SourcecodeScholar