Extended Abstract

Differentiable Tree Operations Promote Compositional Generalization

Authors: Paul Soulos (Johns Hopkins University) , Edward Hu (Mila) , Kate McCurdy (University of Edinburgh) , Yunmo Chen (Johns Hopkins University) , Roland Fernandez (Microsoft Research) , Paul Smolensky (Johns Hopkins University / Microsoft Research, Redmond) , Jianfeng Gao (Microsoft Research)

Abstract

Keywords: Compositionality, Generalization, Neurosymbolic, Natural Language Processing, Differentiable Computing, Trees, Vector Symbolic Architecture, Hyperdimensional Computing

How to Cite: Soulos, P. , Hu, E. , McCurdy, K. , Chen, Y. , Fernandez, R. , Smolensky, P. & Gao, J. (2023) “Differentiable Tree Operations Promote Compositional Generalization”, Society for Computation in Linguistics. 6(1). doi: https://doi.org/10.7275/n99s-pp43