26 citations · 30 across the 7 of their papers we have counts for
7 papers
The Emergent Symbolic Structure of Artificial Neural Networks
R. Thomas McCoy, Paul Soulos, Tal Linzen +1
Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modeled as operating over structured…
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Paul Soulos, Henry Conklin, Mattia Opper +3
Neural networks continue to struggle with compositional generalization, and this issue is exacerbated by a lack of massive pre-training. One successful approach for developing neur…
Differentiable Tree Operations Promote Compositional Generalization
Paul Soulos, Edward Hu, Kate McCurdy +4
In the context of structure-to-structure transformation tasks, learning sequences of discrete symbolic operations poses significant challenges due to their non-differentiability. T…
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Paul Soulos, Sudha Rao, Caitlin Smith +9
Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still impl…
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
Yichen Jiang, Asli Celikyilmaz, Paul Smolensky +7
Abstractive summarization, the task of generating a concise summary of input documents, requires: (1) reasoning over the source document to determine the salient pieces of informat…
Discovering the Compositional Structure of Vector Representations with Role Learning Networks
Paul Soulos, Tom McCoy, Tal Linzen +1
How can neural networks perform so well on compositional tasks even though they lack explicit compositional representations? We use a novel analysis technique called ROLE to show t…
Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels
Joshua C. Peterson, Paul Soulos, Aida Nematzadeh +1
Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explainin…