<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2017-cascading">
    <titleInfo>
        <title>Cascading Multiway Attentions for Document-level Sentiment Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dehong</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sujian</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaodong</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Houfeng</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xu</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
        </titleInfo>
        <originInfo>
            <publisher>Asian Federation of Natural Language Processing</publisher>
            <place>
                <placeTerm type="text">Taipei, Taiwan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Document-level sentiment classification aims to assign the user reviews a sentiment polarity. Previous methods either just utilized the document content without consideration of user and product information, or did not comprehensively consider what roles the three kinds of information play in text modeling. In this paper, to reasonably use all the information, we present the idea that user, product and their combination can all influence the generation of attentions to words and sentences, when judging the sentiment of a document. With this idea, we propose a cascading multiway attention (CMA) model, where multiple ways of using user and product information are cascaded to influence the generation of attentions on the word and sentence layers. Then, sentences and documents are well modeled by multiple representation vectors, which provide rich information for sentiment classification. Experiments on IMDB and Yelp datasets demonstrate the effectiveness of our model.</abstract>
    <identifier type="citekey">ma-etal-2017-cascading</identifier>
    <location>
        <url>https://aclanthology.org/I17-1064</url>
    </location>
    <part>
        <date>2017-nov</date>
        <extent unit="page">
            <start>634</start>
            <end>643</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cascading Multiway Attentions for Document-level Sentiment Classification
%A Ma, Dehong
%A Li, Sujian
%A Zhang, Xiaodong
%A Wang, Houfeng
%A Sun, Xu
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2017
%8 nov
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F ma-etal-2017-cascading
%X Document-level sentiment classification aims to assign the user reviews a sentiment polarity. Previous methods either just utilized the document content without consideration of user and product information, or did not comprehensively consider what roles the three kinds of information play in text modeling. In this paper, to reasonably use all the information, we present the idea that user, product and their combination can all influence the generation of attentions to words and sentences, when judging the sentiment of a document. With this idea, we propose a cascading multiway attention (CMA) model, where multiple ways of using user and product information are cascaded to influence the generation of attentions on the word and sentence layers. Then, sentences and documents are well modeled by multiple representation vectors, which provide rich information for sentiment classification. Experiments on IMDB and Yelp datasets demonstrate the effectiveness of our model.
%U https://aclanthology.org/I17-1064
%P 634-643

Markdown (Informal)

[Cascading Multiway Attentions for Document-level Sentiment Classification](https://aclanthology.org/I17-1064) (Ma et al., IJCNLP 2017)

• Cascading Multiway Attentions for Document-level Sentiment Classification (Ma et al., IJCNLP 2017)

ACL

• Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang, and Xu Sun. 2017. Cascading Multiway Attentions for Document-level Sentiment Classification. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 634–643, Taipei, Taiwan. Asian Federation of Natural Language Processing.