Search Results for author:
Found 6 papers, 3 papers with code
Differentiable Tree Operations Promote Compositional Generalization
To facilitate the learning of these symbolic sequences, we introduce a differentiable tree interpreter that compiles high-level symbolic tree operations into subsymbolic matrix operations on tensors.
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Machine translation has seen rapid progress with the advent of Transformer-based models.
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and improved syntactic interpretability in the TPR layer outputs.
Disentangled Face Representations in Deep Generative Models and the Human Brain
We further find that the latent dimensions in these models map onto non-overlapping regions in fMRI data, allowing us to "disentangle" different features such as 3D rotation, skin tone, and facial expression in the human brain.
Discovering the Compositional Structure of Vector Representations with Role Learning Networks
How can neural networks perform so well on compositional tasks even though they lack explicit compositional representations?
Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels
Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations.
