<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amram-etal-2018-representations">
    <titleInfo>
        <title>Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Amram</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anat</namePart>
        <namePart type="family">Ben David</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Reut</namePart>
        <namePart type="family">Tsarfaty</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 27th International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Emily</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Bender</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leon</namePart>
            <namePart type="family">Derczynski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Pierre</namePart>
            <namePart type="family">Isabelle</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper empirically studies the effects of representation choices on neural sentiment analysis for Modern Hebrew, a morphologically rich language (MRL) for which no sentiment analyzer currently exists. We study two dimensions of representational choices: (i) the granularity of the input signal (token-based vs. morpheme-based), and (ii) the level of encoding of vocabulary items (string-based vs. character-based). We hypothesise that for MRLs, languages where multiple meaning-bearing elements may be carried by a single space-delimited token, these choices will have measurable effects on task perfromance, and that these effects may vary for different architectural designs — fully-connected, convolutional or recurrent. Specifically, we hypothesize that morpheme-based representations will have advantages in terms of their generalization capacity and task accuracy, due to their better OOV coverage. To empirically study these effects, we develop a new sentiment analysis benchmark for Hebrew, based on 12K social media comments, and provide two instances of these data: in token-based and morpheme-based settings. Our experiments show that representation choices empirical effects vary with architecture type. While fully-connected and convolutional networks slightly prefer token-based settings, RNNs benefit from a morpheme-based representation, in accord with the hypothesis that explicit morphological information may help generalize. Our endeavour also delivers the first state-of-the-art broad-coverage sentiment analyzer for Hebrew, with over 89% accuracy, alongside an established benchmark to further study the effects of linguistic representation choices on neural networks’ task performance.</abstract>
    <identifier type="citekey">amram-etal-2018-representations</identifier>
    <location>
        <url>https://aclanthology.org/C18-1190</url>
    </location>
    <part>
        <date>2018-08</date>
        <extent unit="page">
            <start>2242</start>
            <end>2252</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew
%A Amram, Adam
%A Ben David, Anat
%A Tsarfaty, Reut
%Y Bender, Emily M.
%Y Derczynski, Leon
%Y Isabelle, Pierre
%S Proceedings of the 27th International Conference on Computational Linguistics
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F amram-etal-2018-representations
%X This paper empirically studies the effects of representation choices on neural sentiment analysis for Modern Hebrew, a morphologically rich language (MRL) for which no sentiment analyzer currently exists. We study two dimensions of representational choices: (i) the granularity of the input signal (token-based vs. morpheme-based), and (ii) the level of encoding of vocabulary items (string-based vs. character-based). We hypothesise that for MRLs, languages where multiple meaning-bearing elements may be carried by a single space-delimited token, these choices will have measurable effects on task perfromance, and that these effects may vary for different architectural designs — fully-connected, convolutional or recurrent. Specifically, we hypothesize that morpheme-based representations will have advantages in terms of their generalization capacity and task accuracy, due to their better OOV coverage. To empirically study these effects, we develop a new sentiment analysis benchmark for Hebrew, based on 12K social media comments, and provide two instances of these data: in token-based and morpheme-based settings. Our experiments show that representation choices empirical effects vary with architecture type. While fully-connected and convolutional networks slightly prefer token-based settings, RNNs benefit from a morpheme-based representation, in accord with the hypothesis that explicit morphological information may help generalize. Our endeavour also delivers the first state-of-the-art broad-coverage sentiment analyzer for Hebrew, with over 89% accuracy, alongside an established benchmark to further study the effects of linguistic representation choices on neural networks’ task performance.
%U https://aclanthology.org/C18-1190
%P 2242-2252

Markdown (Informal)

[Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew](https://aclanthology.org/C18-1190) (Amram et al., COLING 2018)

• Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew (Amram et al., COLING 2018)

ACL

• Adam Amram, Anat Ben David, and Reut Tsarfaty. 2018. Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2242–2252, Santa Fe, New Mexico, USA. Association for Computational Linguistics.