<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2020-octa">
    <titleInfo>
        <title>Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhe</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chung-Wei</namePart>
        <namePart type="family">Hang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Munindar</namePart>
        <namePart type="family">Singh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Sentiments in opinionated text are often determined by both aspects and target words (or targets). We observe that targets and aspects interrelate in subtle ways, often yielding conflicting sentiments. Thus, a naive aggregation of sentiments from aspects and targets treated separately, as in existing sentiment analysis models, impairs performance. We propose Octa, an approach that jointly considers aspects and targets when inferring sentiments. To capture and quantify relationships between targets and context words, Octa uses a selective self-attention mechanism that handles implicit or missing targets. Specifically, Octa involves two layers of attention mechanisms for, respectively, selective attention between targets and context words and attention over words based on aspects. On benchmark datasets, Octa outperforms leading models by a large margin, yielding (absolute) gains in accuracy of 1.6% to 4.3%.</abstract>
    <identifier type="citekey">zhang-etal-2020-octa</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.149</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.149</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>1651</start>
            <end>1662</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis
%A Zhang, Zhe
%A Hang, Chung-Wei
%A Singh, Munindar
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zhang-etal-2020-octa
%X Sentiments in opinionated text are often determined by both aspects and target words (or targets). We observe that targets and aspects interrelate in subtle ways, often yielding conflicting sentiments. Thus, a naive aggregation of sentiments from aspects and targets treated separately, as in existing sentiment analysis models, impairs performance. We propose Octa, an approach that jointly considers aspects and targets when inferring sentiments. To capture and quantify relationships between targets and context words, Octa uses a selective self-attention mechanism that handles implicit or missing targets. Specifically, Octa involves two layers of attention mechanisms for, respectively, selective attention between targets and context words and attention over words based on aspects. On benchmark datasets, Octa outperforms leading models by a large margin, yielding (absolute) gains in accuracy of 1.6% to 4.3%.
%R 10.18653/v1/2020.findings-emnlp.149
%U https://aclanthology.org/2020.findings-emnlp.149
%U https://doi.org/10.18653/v1/2020.findings-emnlp.149
%P 1651-1662

Markdown (Informal)

[Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis](https://aclanthology.org/2020.findings-emnlp.149) (Zhang et al., Findings 2020)

• Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis (Zhang et al., Findings 2020)

ACL

• Zhe Zhang, Chung-Wei Hang, and Munindar Singh. 2020. Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1651–1662, Online. Association for Computational Linguistics.