14 citations · 18 across the 18 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022
Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
Satwik Bhattamishra, Arkil Patel, Varun Kanade +1
Despite the widespread success of Transformers on NLP tasks, recent works have found that they struggle to model several formal languages when compared to recurrent models. This ra…
cs.CL2022
Revisiting the Compositional Generalization Abilities of Neural Sequence Models
Arkil Patel, Satwik Bhattamishra, Phil Blunsom +1
Compositional generalization is a fundamental trait in humans, allowing us to effortlessly combine known phrases to form novel sentences. Recent works have claimed that standard se…