<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="novikova-etal-2019-lexical">
    <titleInfo>
        <title>Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jekaterina</namePart>
        <namePart type="family">Novikova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aparna</namePart>
        <namePart type="family">Balagopalan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ksenia</namePart>
        <namePart type="family">Shkaruta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Frank</namePart>
        <namePart type="family">Rudzicz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wei</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tim</namePart>
            <namePart type="family">Baldwin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Afshin</namePart>
            <namePart type="family">Rahimi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Understanding the vulnerability of linguistic features extracted from noisy text is important for both developing better health text classification models and for interpreting vulnerabilities of natural language models. In this paper, we investigate how generic language characteristics, such as syntax or the lexicon, are impacted by artificial text alterations. The vulnerability of features is analysed from two perspectives: (1) the level of feature value change, and (2) the level of change of feature predictive power as a result of text modifications. We show that lexical features are more sensitive to text modifications than syntactic ones. However, we also demonstrate that these smaller changes of syntactic features have a stronger influence on classification performance downstream, compared to the impact of changes to lexical features. Results are validated across three datasets representing different text-classification tasks, with different levels of lexical and syntactic complexity of both conversational and written language.</abstract>
    <identifier type="citekey">novikova-etal-2019-lexical</identifier>
    <identifier type="doi">10.18653/v1/D19-5556</identifier>
    <location>
        <url>https://aclanthology.org/D19-5556</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>431</start>
            <end>443</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power
%A Novikova, Jekaterina
%A Balagopalan, Aparna
%A Shkaruta, Ksenia
%A Rudzicz, Frank
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F novikova-etal-2019-lexical
%X Understanding the vulnerability of linguistic features extracted from noisy text is important for both developing better health text classification models and for interpreting vulnerabilities of natural language models. In this paper, we investigate how generic language characteristics, such as syntax or the lexicon, are impacted by artificial text alterations. The vulnerability of features is analysed from two perspectives: (1) the level of feature value change, and (2) the level of change of feature predictive power as a result of text modifications. We show that lexical features are more sensitive to text modifications than syntactic ones. However, we also demonstrate that these smaller changes of syntactic features have a stronger influence on classification performance downstream, compared to the impact of changes to lexical features. Results are validated across three datasets representing different text-classification tasks, with different levels of lexical and syntactic complexity of both conversational and written language.
%R 10.18653/v1/D19-5556
%U https://aclanthology.org/D19-5556
%U https://doi.org/10.18653/v1/D19-5556
%P 431-443

Markdown (Informal)

[Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power](https://aclanthology.org/D19-5556) (Novikova et al., WNUT 2019)

• Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power (Novikova et al., WNUT 2019)

ACL

• Jekaterina Novikova, Aparna Balagopalan, Ksenia Shkaruta, and Frank Rudzicz. 2019. Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pages 431–443, Hong Kong, China. Association for Computational Linguistics.