<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cercas-curry-rieser-2018-metoo">
    <titleInfo>
        <title>#MeToo Alexa: How Conversational Systems Respond to Sexual Harassment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Amanda</namePart>
        <namePart type="family">Cercas Curry</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Verena</namePart>
        <namePart type="family">Rieser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second ACL Workshop on Ethics in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mark</namePart>
            <namePart type="family">Alfano</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dirk</namePart>
            <namePart type="family">Hovy</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Margaret</namePart>
            <namePart type="family">Mitchell</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">Strube</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans, Louisiana, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Conversational AI systems, such as Amazon’s Alexa, are rapidly developing from purely transactional systems to social chatbots, which can respond to a wide variety of user requests. In this article, we establish how current state-of-the-art conversational systems react to inappropriate requests, such as bullying and sexual harassment on the part of the user, by collecting and analysing the novel #MeTooAlexa corpus. Our results show that commercial systems mainly avoid answering, while rule-based chatbots show a variety of behaviours and often deflect. Data-driven systems, on the other hand, are often non-coherent, but also run the risk of being interpreted as flirtatious and sometimes react with counter-aggression. This includes our own system, trained on “clean” data, which suggests that inappropriate system behaviour is not caused by data bias.</abstract>
    <identifier type="citekey">cercas-curry-rieser-2018-metoo</identifier>
    <identifier type="doi">10.18653/v1/W18-0802</identifier>
    <location>
        <url>https://aclanthology.org/W18-0802</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>7</start>
            <end>14</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T #MeToo Alexa: How Conversational Systems Respond to Sexual Harassment
%A Cercas Curry, Amanda
%A Rieser, Verena
%Y Alfano, Mark
%Y Hovy, Dirk
%Y Mitchell, Margaret
%Y Strube, Michael
%S Proceedings of the Second ACL Workshop on Ethics in Natural Language Processing
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana, USA
%F cercas-curry-rieser-2018-metoo
%X Conversational AI systems, such as Amazon’s Alexa, are rapidly developing from purely transactional systems to social chatbots, which can respond to a wide variety of user requests. In this article, we establish how current state-of-the-art conversational systems react to inappropriate requests, such as bullying and sexual harassment on the part of the user, by collecting and analysing the novel #MeTooAlexa corpus. Our results show that commercial systems mainly avoid answering, while rule-based chatbots show a variety of behaviours and often deflect. Data-driven systems, on the other hand, are often non-coherent, but also run the risk of being interpreted as flirtatious and sometimes react with counter-aggression. This includes our own system, trained on “clean” data, which suggests that inappropriate system behaviour is not caused by data bias.
%R 10.18653/v1/W18-0802
%U https://aclanthology.org/W18-0802
%U https://doi.org/10.18653/v1/W18-0802
%P 7-14

Markdown (Informal)

[#MeToo Alexa: How Conversational Systems Respond to Sexual Harassment](https://aclanthology.org/W18-0802) (Cercas Curry & Rieser, EthNLP 2018)

• #MeToo Alexa: How Conversational Systems Respond to Sexual Harassment (Cercas Curry & Rieser, EthNLP 2018)

ACL

• Amanda Cercas Curry and Verena Rieser. 2018. #MeToo Alexa: How Conversational Systems Respond to Sexual Harassment. In Proceedings of the Second ACL Workshop on Ethics in Natural Language Processing, pages 7–14, New Orleans, Louisiana, USA. Association for Computational Linguistics.