Improving Compositional Generalization in Classification Tasks via Structure Annotations

06/19/2021
by   Juyong Kim, et al.
0

Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-art neural models struggle to do so. In this work, we study compositional generalization in classification tasks and present two main contributions. First, we study ways to convert a natural language sequence-to-sequence dataset to a classification dataset that also requires compositional generalization. Second, we show that providing structural hints (specifically, providing parse trees and entity links as attention masks for a Transformer model) helps compositional generalization.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset