Differentiable Tree Operations Promote Compositional Generalization
- 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)
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), 364-374. doi: https://doi.org/10.7275/n99s-pp43
Downloads:
Download PDF