Search Results for author:
Found 11 papers, 7 papers with code
Implicit Chain of Thought Reasoning via Knowledge Distillation
In this work, we explore an alternative reasoning approach: instead of explicitly producing the chain of thought reasoning steps, we use the language model's internal hidden states to perform implicit reasoning.
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.
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, and how can the remaining limitations of current AI be overcome?
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.
Compositional Processing Emerges in Neural Networks Solving Math Problems
A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition.
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
In this paper, we propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning.
A System for Real-Time Interactive Analysis of Deep Learning Training
To achieve this, we model various exploratory inspection and diagnostic tasks for deep learning training processes as specifications for streams using a map-reduce paradigm with which many data scientists are already familiar.
Working Memory Graphs
Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences.
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure.
Ranked #1 on
Question Answering
on Mathematics Dataset
Learning and analyzing vector encoding of symbolic representations
We present a formal language with expressions denoting general symbol structures and queries which access information in those structures.
