@inproceedings{gao-etal-2018-hierarchical,
title = "Hierarchical Convolutional Attention Networks for Text Classification",
author = "Gao, Shang and
Ramanathan, Arvind and
Tourassi, Georgia",
editor = "Augenstein, Isabelle and
Cao, Kris and
He, He and
Hill, Felix and
Gella, Spandana and
Kiros, Jamie and
Mei, Hongyuan and
Misra, Dipendra",
booktitle = "Proceedings of the Third Workshop on Representation Learning for {NLP}",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3002",
doi = "10.18653/v1/W18-3002",
pages = "11--23",
abstract = "Recent work in machine translation has demonstrated that self-attention mechanisms can be used in place of recurrent neural networks to increase training speed without sacrificing model accuracy. We propose combining this approach with the benefits of convolutional filters and a hierarchical structure to create a document classification model that is both highly accurate and fast to train {--} we name our method Hierarchical Convolutional Attention Networks. We demonstrate the effectiveness of this architecture by surpassing the accuracy of the current state-of-the-art on several classification tasks while being twice as fast to train.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2018-hierarchical">
<titleInfo>
<title>Hierarchical Convolutional Attention Networks for Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvind</namePart>
<namePart type="family">Ramanathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgia</namePart>
<namePart type="family">Tourassi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Hill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamie</namePart>
<namePart type="family">Kiros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyuan</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipendra</namePart>
<namePart type="family">Misra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work in machine translation has demonstrated that self-attention mechanisms can be used in place of recurrent neural networks to increase training speed without sacrificing model accuracy. We propose combining this approach with the benefits of convolutional filters and a hierarchical structure to create a document classification model that is both highly accurate and fast to train – we name our method Hierarchical Convolutional Attention Networks. We demonstrate the effectiveness of this architecture by surpassing the accuracy of the current state-of-the-art on several classification tasks while being twice as fast to train.</abstract>
<identifier type="citekey">gao-etal-2018-hierarchical</identifier>
<identifier type="doi">10.18653/v1/W18-3002</identifier>
<location>
<url>https://aclanthology.org/W18-3002</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>11</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Convolutional Attention Networks for Text Classification
%A Gao, Shang
%A Ramanathan, Arvind
%A Tourassi, Georgia
%Y Augenstein, Isabelle
%Y Cao, Kris
%Y He, He
%Y Hill, Felix
%Y Gella, Spandana
%Y Kiros, Jamie
%Y Mei, Hongyuan
%Y Misra, Dipendra
%S Proceedings of the Third Workshop on Representation Learning for NLP
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F gao-etal-2018-hierarchical
%X Recent work in machine translation has demonstrated that self-attention mechanisms can be used in place of recurrent neural networks to increase training speed without sacrificing model accuracy. We propose combining this approach with the benefits of convolutional filters and a hierarchical structure to create a document classification model that is both highly accurate and fast to train – we name our method Hierarchical Convolutional Attention Networks. We demonstrate the effectiveness of this architecture by surpassing the accuracy of the current state-of-the-art on several classification tasks while being twice as fast to train.
%R 10.18653/v1/W18-3002
%U https://aclanthology.org/W18-3002
%U https://doi.org/10.18653/v1/W18-3002
%P 11-23
Markdown (Informal)
[Hierarchical Convolutional Attention Networks for Text Classification](https://aclanthology.org/W18-3002) (Gao et al., RepL4NLP 2018)
ACL