Neural Associative Memory for Dual-Sequence Modeling

TL;DR

This paper introduces a novel neural architecture called Dual AM-RNN, based on associative memory, designed for dual-sequence NLP tasks, showing promising results in textual entailment and long-range dependency modeling.

Contribution

It proposes a new dual-sequence neural model using associative memory, extending RNNs to better capture dependencies in sequence-to-sequence tasks.

Findings

Achieves competitive results on textual entailment.

Effectively bridges long-range dependencies.

Needs additional supervision for sequence-to-sequence tasks.

Abstract

Many important NLP problems can be posed as dual-sequence or sequence-to-sequence modeling tasks. Recent advances in building end-to-end neural architectures have been highly successful in solving such tasks. In this work we propose a new architecture for dual-sequence modeling that is based on associative memory. We derive AM-RNNs, a recurrent associative memory (AM) which augments generic recurrent neural networks (RNN). This architecture is extended to the Dual AM-RNN which operates on two AMs at once. Our models achieve very competitive results on textual entailment. A qualitative analysis demonstrates that long range dependencies between source and target-sequence can be bridged effectively using Dual AM-RNNs. However, an initial experiment on auto-encoding reveals that these benefits are not exploited by the system when learning to solve sequence-to-sequence tasks which indicates that additional supervision or regularization is needed.