@inproceedings{ambartsoumian-popowich-2018-self,
title = "Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers",
author = "Ambartsoumian, Artaches and
Popowich, Fred",
editor = "Balahur, Alexandra and
Mohammad, Saif M. and
Hoste, Veronique and
Klinger, Roman",
booktitle = "Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6219",
doi = "10.18653/v1/W18-6219",
pages = "130--139",
abstract = "Sentiment Analysis has seen much progress in the past two decades. For the past few years, neural network approaches, primarily RNNs and CNNs, have been the most successful for this task. Recently, a new category of neural networks, self-attention networks (SANs), have been created which utilizes the attention mechanism as the basic building block. Self-attention networks have been shown to be effective for sequence modeling tasks, while having no recurrence or convolutions. In this work we explore the effectiveness of the SANs for sentiment analysis. We demonstrate that SANs are superior in performance to their RNN and CNN counterparts by comparing their classification accuracy on six datasets as well as their model characteristics such as training speed and memory consumption. Finally, we explore the effects of various SAN modifications such as multi-head attention as well as two methods of incorporating sequence position information into SANs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ambartsoumian-popowich-2018-self">
<titleInfo>
<title>Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Artaches</namePart>
<namePart type="family">Ambartsoumian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fred</namePart>
<namePart type="family">Popowich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment Analysis has seen much progress in the past two decades. For the past few years, neural network approaches, primarily RNNs and CNNs, have been the most successful for this task. Recently, a new category of neural networks, self-attention networks (SANs), have been created which utilizes the attention mechanism as the basic building block. Self-attention networks have been shown to be effective for sequence modeling tasks, while having no recurrence or convolutions. In this work we explore the effectiveness of the SANs for sentiment analysis. We demonstrate that SANs are superior in performance to their RNN and CNN counterparts by comparing their classification accuracy on six datasets as well as their model characteristics such as training speed and memory consumption. Finally, we explore the effects of various SAN modifications such as multi-head attention as well as two methods of incorporating sequence position information into SANs.</abstract>
<identifier type="citekey">ambartsoumian-popowich-2018-self</identifier>
<identifier type="doi">10.18653/v1/W18-6219</identifier>
<location>
<url>https://aclanthology.org/W18-6219</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>130</start>
<end>139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers
%A Ambartsoumian, Artaches
%A Popowich, Fred
%Y Balahur, Alexandra
%Y Mohammad, Saif M.
%Y Hoste, Veronique
%Y Klinger, Roman
%S Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F ambartsoumian-popowich-2018-self
%X Sentiment Analysis has seen much progress in the past two decades. For the past few years, neural network approaches, primarily RNNs and CNNs, have been the most successful for this task. Recently, a new category of neural networks, self-attention networks (SANs), have been created which utilizes the attention mechanism as the basic building block. Self-attention networks have been shown to be effective for sequence modeling tasks, while having no recurrence or convolutions. In this work we explore the effectiveness of the SANs for sentiment analysis. We demonstrate that SANs are superior in performance to their RNN and CNN counterparts by comparing their classification accuracy on six datasets as well as their model characteristics such as training speed and memory consumption. Finally, we explore the effects of various SAN modifications such as multi-head attention as well as two methods of incorporating sequence position information into SANs.
%R 10.18653/v1/W18-6219
%U https://aclanthology.org/W18-6219
%U https://doi.org/10.18653/v1/W18-6219
%P 130-139
Markdown (Informal)
[Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers](https://aclanthology.org/W18-6219) (Ambartsoumian & Popowich, WASSA 2018)
ACL