research
∙
06/01/2023
Differentiable Tree Operations Promote Compositional Generalization
In the context of structure-to-structure transformation tasks, learning ...
share
research
∙
08/11/2022
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Machine translation has seen rapid progress with the advent of Transform...
research
∙
05/02/2022
Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems
What explains the dramatic progress from 20th-century to 21st-century AI...
research
∙
06/02/2021
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
Abstractive summarization, the task of generating a concise summary of i...
research
∙
05/19/2021
Compositional Processing Emerges in Neural Networks Solving Math Problems
A longstanding question in cognitive science concerns the learning mecha...
research
∙
11/18/2020
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
Neuro-symbolic representations have proved effective in learning structu...
research
∙
11/17/2019
Working Memory Graphs
Transformers have increasingly outperformed gated RNNs in obtaining new ...
research
∙
10/15/2019
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
We incorporate Tensor-Product Representations within the Transformer in ...
research
∙
03/10/2018
