Deep neural networks (DNN) have revolutionized the field of natural language
processing (NLP). Convolutional neural network (CNN) and recurrent neural
network (RNN), the two main types of DNN architectures, are widely explored to
handle various NLP tasks. CNN is supposed to be good at extracting
position-invariant features and RNN at modeling units in sequence. The state of
the art on many NLP tasks often switches due to the battle between CNNs and
RNNs. This work is the first systematic comparison of CNN and RNN on a wide
range of representative NLP tasks, aiming to give basic guidance for DNN
selection.
Description
[1702.01923] Comparative Study of CNN and RNN for Natural Language Processing
%0 Generic
%1 yin2017comparative
%A Yin, Wenpeng
%A Kann, Katharina
%A Yu, Mo
%A Schütze, Hinrich
%D 2017
%K cnn comparison network neural nlp rnn
%T Comparative Study of CNN and RNN for Natural Language Processing
%U http://arxiv.org/abs/1702.01923
%X Deep neural networks (DNN) have revolutionized the field of natural language
processing (NLP). Convolutional neural network (CNN) and recurrent neural
network (RNN), the two main types of DNN architectures, are widely explored to
handle various NLP tasks. CNN is supposed to be good at extracting
position-invariant features and RNN at modeling units in sequence. The state of
the art on many NLP tasks often switches due to the battle between CNNs and
RNNs. This work is the first systematic comparison of CNN and RNN on a wide
range of representative NLP tasks, aiming to give basic guidance for DNN
selection.
@misc{yin2017comparative,
abstract = {Deep neural networks (DNN) have revolutionized the field of natural language
processing (NLP). Convolutional neural network (CNN) and recurrent neural
network (RNN), the two main types of DNN architectures, are widely explored to
handle various NLP tasks. CNN is supposed to be good at extracting
position-invariant features and RNN at modeling units in sequence. The state of
the art on many NLP tasks often switches due to the battle between CNNs and
RNNs. This work is the first systematic comparison of CNN and RNN on a wide
range of representative NLP tasks, aiming to give basic guidance for DNN
selection.},
added-at = {2018-06-08T12:01:01.000+0200},
author = {Yin, Wenpeng and Kann, Katharina and Yu, Mo and Schütze, Hinrich},
biburl = {https://www.bibsonomy.org/bibtex/24b849c91fa49f7927fafdef55e5ab2c5/nosebrain},
description = {[1702.01923] Comparative Study of CNN and RNN for Natural Language Processing},
interhash = {ecf24d32d12a3c62b6bd42da9ebb423b},
intrahash = {4b849c91fa49f7927fafdef55e5ab2c5},
keywords = {cnn comparison network neural nlp rnn},
note = {cite arxiv:1702.01923Comment: 7 pages, 11 figures},
timestamp = {2018-06-08T12:01:01.000+0200},
title = {Comparative Study of CNN and RNN for Natural Language Processing},
url = {http://arxiv.org/abs/1702.01923},
year = 2017
}