Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack
release_yggpyk3eafefbkmzgfapyror4i
by
Ankur Mali, Alexander Ororbia, Daniel Kifer, Clyde Lee Giles
2020
Abstract
Recurrent neural networks (RNNs) are a widely used deep architecture for
sequence modeling, generation, and prediction. Despite success in applications
such as machine translation and voice recognition, these stateful models have
several critical shortcomings. Specifically, RNNs generalize poorly over very
long sequences, which limits their applicability to many important temporal
processing and time series forecasting problems. For example, RNNs struggle in
recognizing complex context free languages (CFLs), never reaching 100% accuracy
on training. One way to address these shortcomings is to couple an RNN with an
external, differentiable memory structure, such as a stack. However,
differentiable memories in prior work have neither been extensively studied on
CFLs nor tested on sequences longer than those seen in training. The few
efforts that have studied them have shown that continuous differentiable memory
structures yield poor generalization for complex CFLs, making the RNN less
interpretable. In this paper, we improve the memory-augmented RNN with
important architectural and state updating mechanisms that ensure that the
model learns to properly balance the use of its latent states with external
memory. Our improved RNN models exhibit better generalization performance and
are able to classify long strings generated by complex hierarchical context
free grammars (CFGs). We evaluate our models on CGGs, including the Dyck
languages, as well as on the Penn Treebank language modelling task, and achieve
stable, robust performance across these benchmarks. Furthermore, we show that
only our memory-augmented networks are capable of retaining memory for a longer
duration up to strings of length 160.
In text/plain
format
Archived Files and Locations
application/pdf 241.3 kB
file_4vqhyilqlncsrmq4tuqygks57i
|
arxiv.org (repository) web.archive.org (webarchive) |
2004.07623v1
access all versions, variants, and formats of this works (eg, pre-prints)