Neural Associative Memory for Dual-Sequence Modeling
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.
Cite
@article{arxiv.1606.03864,
title = {Neural Associative Memory for Dual-Sequence Modeling},
author = {Dirk Weissenborn},
journal= {arXiv preprint arXiv:1606.03864},
year = {2016}
}
Comments
To appear in RepL4NLP at ACL 2016