Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages
Abstract
We introduce three memory-augmented Recurrent Neural Networks (MARNNs) and explore their capabilities on a series of simple language modeling tasks whose solutions require stack-based mechanisms. We provide the first demonstration of neural networks recognizing the generalized Dyck languages, which express the core of what it means to be a language with hierarchical structure. Our memory-augmented architectures are easy to train in an end-to-end fashion and can learn the Dyck languages over as many as six parenthesis-pairs, in addition to two deterministic palindrome languages and the string-reversal transduction task, by emulating pushdown automata. Our experiments highlight the increased modeling capacity of memory-augmented models over simple RNNs, while inflecting our understanding of the limitations of these models.
Cite
@article{arxiv.1911.03329,
title = {Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages},
author = {Mirac Suzgun and Sebastian Gehrmann and Yonatan Belinkov and Stuart M. Shieber},
journal= {arXiv preprint arXiv:1911.03329},
year = {2019}
}