@inproceedings{chen-etal-2020-inducing,
title = "Inducing Target-Specific Latent Structures for Aspect Sentiment Classification",
author = "Chen, Chenhua and
Teng, Zhiyang and
Zhang, Yue",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.451",
doi = "10.18653/v1/2020.emnlp-main.451",
pages = "5596--5607",
abstract = "Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied for this task. However, the dependency parsing accuracy of commercial product comments or tweets might be unsatisfactory. To tackle this problem, we associate linguistic dependency trees with automatically induced aspectspecific graphs. We propose gating mechanisms to dynamically combine information from word dependency graphs and latent graphs which are learned by self-attention networks. Our model can complement supervised syntactic features with latent semantic dependencies. Experimental results on five benchmarks show the effectiveness of our proposed latent models, giving significantly better results than models without using latent graphs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-inducing">
<titleInfo>
<title>Inducing Target-Specific Latent Structures for Aspect Sentiment Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenhua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyang</namePart>
<namePart type="family">Teng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied for this task. However, the dependency parsing accuracy of commercial product comments or tweets might be unsatisfactory. To tackle this problem, we associate linguistic dependency trees with automatically induced aspectspecific graphs. We propose gating mechanisms to dynamically combine information from word dependency graphs and latent graphs which are learned by self-attention networks. Our model can complement supervised syntactic features with latent semantic dependencies. Experimental results on five benchmarks show the effectiveness of our proposed latent models, giving significantly better results than models without using latent graphs.</abstract>
<identifier type="citekey">chen-etal-2020-inducing</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.451</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.451</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>5596</start>
<end>5607</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inducing Target-Specific Latent Structures for Aspect Sentiment Classification
%A Chen, Chenhua
%A Teng, Zhiyang
%A Zhang, Yue
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F chen-etal-2020-inducing
%X Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied for this task. However, the dependency parsing accuracy of commercial product comments or tweets might be unsatisfactory. To tackle this problem, we associate linguistic dependency trees with automatically induced aspectspecific graphs. We propose gating mechanisms to dynamically combine information from word dependency graphs and latent graphs which are learned by self-attention networks. Our model can complement supervised syntactic features with latent semantic dependencies. Experimental results on five benchmarks show the effectiveness of our proposed latent models, giving significantly better results than models without using latent graphs.
%R 10.18653/v1/2020.emnlp-main.451
%U https://aclanthology.org/2020.emnlp-main.451
%U https://doi.org/10.18653/v1/2020.emnlp-main.451
%P 5596-5607
Markdown (Informal)
[Inducing Target-Specific Latent Structures for Aspect Sentiment Classification](https://aclanthology.org/2020.emnlp-main.451) (Chen et al., EMNLP 2020)
ACL