
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
We incorporate TensorProduct Representations within the Transformer in ...
read it

Tensor Product Generation Networks
We present a new tensor product generation network (TPGN) that generates...
read it

Basic Reasoning with Tensor Product Representations
In this paper we present the initial development of a general theory for...
read it

A NeuralSymbolic Approach to Natural Language Tasks
Deep learning (DL) has in recent years been widely used in natural langu...
read it

Tensor Product Generation Networks for Deep NLP Modeling
We present a new approach to the design of deep networks for natural lan...
read it

QuestionAnswering with GrammaticallyInterpretable Representations
We introduce an architecture, the Tensor Product Recurrent Network (TPRN...
read it

Reasoning in Vector Space: An Exploratory Study of Question Answering
Question answering tasks have shown remarkable progress with distributed...
read it

Discrete symbolic optimization and Boltzmann sampling by continuous neural dynamics: Gradient Symbolic Computation
Gradient Symbolic Computation is proposed as a means of solving discrete...
read it

Learning and analyzing vector encoding of symbolic representations
We present a formal language with expressions denoting general symbol st...
read it

Predicting Argumenthood of English Preposition Phrases
Distinguishing between core and noncore dependents (i.e., arguments and...
read it

Learning Distributed Representations of Symbolic Structure Using Binding and Unbinding Operations
Widely used recurrent units, including Longshort Term Memory (LSTM) and...
read it

Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations
Neural models of Knowledge Base data have typically employed composition...
read it

RNNs Implicitly Implement Tensor Product Representations
Recurrent neural networks (RNNs) can learn continuous vector representat...
read it

Natural to formallanguage generation using Tensor Product Representations
Generating formallanguage represented by relational tuples, such as Lis...
read it

Discovering the Compositional Structure of Vector Representations with Role Learning Networks
Neural networks (NNs) are able to perform tasks that rely on composition...
read it

HUBERT Untangles BERT to Improve Transfer across NLP Tasks
We introduce HUBERT which combines the structuredrepresentational power...
read it

A Simple Recurrent Unit with Reduced Tensor Product Representations
idely used recurrent units, including Longshort Term Memory (LSTM) and ...
read it
Paul Smolensky
is this you? claim profile