The ability to accurately represent sentences is central to language
understanding. We describe a convolutional architecture dubbed the Dynamic
Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of
sentences. The network uses Dynamic k-Max Pooling, a global pooling operation
over linear sequences. The network handles input sentences of varying length
and induces a feature graph over the sentence that is capable of explicitly
capturing short and long-range relations. The network does not rely on a parse
tree and is easily applicable to any language. We test the DCNN in four
experiments: small scale binary and multi-class sentiment prediction, six-way
question classification and Twitter sentiment prediction by distant
supervision. The network achieves excellent performance in the first three
tasks and a greater than 25% error reduction in the last task with respect to
the strongest baseline.
Description
A Convolutional Neural Network for Modelling Sentences
%0 Generic
%1 kalchbrenner2014convolutional
%A Kalchbrenner, Nal
%A Grefenstette, Edward
%A Blunsom, Phil
%D 2014
%K deep_learning thema thema:sentence_modeling
%T A Convolutional Neural Network for Modelling Sentences
%U http://arxiv.org/abs/1404.2188
%X The ability to accurately represent sentences is central to language
understanding. We describe a convolutional architecture dubbed the Dynamic
Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of
sentences. The network uses Dynamic k-Max Pooling, a global pooling operation
over linear sequences. The network handles input sentences of varying length
and induces a feature graph over the sentence that is capable of explicitly
capturing short and long-range relations. The network does not rely on a parse
tree and is easily applicable to any language. We test the DCNN in four
experiments: small scale binary and multi-class sentiment prediction, six-way
question classification and Twitter sentiment prediction by distant
supervision. The network achieves excellent performance in the first three
tasks and a greater than 25% error reduction in the last task with respect to
the strongest baseline.
@misc{kalchbrenner2014convolutional,
abstract = {The ability to accurately represent sentences is central to language
understanding. We describe a convolutional architecture dubbed the Dynamic
Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of
sentences. The network uses Dynamic k-Max Pooling, a global pooling operation
over linear sequences. The network handles input sentences of varying length
and induces a feature graph over the sentence that is capable of explicitly
capturing short and long-range relations. The network does not rely on a parse
tree and is easily applicable to any language. We test the DCNN in four
experiments: small scale binary and multi-class sentiment prediction, six-way
question classification and Twitter sentiment prediction by distant
supervision. The network achieves excellent performance in the first three
tasks and a greater than 25% error reduction in the last task with respect to
the strongest baseline.},
added-at = {2018-03-16T13:39:35.000+0100},
author = {Kalchbrenner, Nal and Grefenstette, Edward and Blunsom, Phil},
biburl = {https://www.bibsonomy.org/bibtex/2cd4f4fcc25ac2ae7bf5a55d490017f19/dallmann},
description = {A Convolutional Neural Network for Modelling Sentences},
interhash = {81260bd862d992b0c3ed72c01a035008},
intrahash = {cd4f4fcc25ac2ae7bf5a55d490017f19},
keywords = {deep_learning thema thema:sentence_modeling},
note = {cite arxiv:1404.2188},
timestamp = {2018-03-16T13:39:35.000+0100},
title = {A Convolutional Neural Network for Modelling Sentences},
url = {http://arxiv.org/abs/1404.2188},
year = 2014
}