<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-etal-2022-distinguish">
    <titleInfo>
        <title>Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Cheng</namePart>
        <namePart type="family">Qian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haode</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gengyu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ladislav</namePart>
        <namePart type="family">Kunc</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saloni</namePart>
        <namePart type="family">Potdar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Angeliki</namePart>
            <namePart type="family">Lazaridou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a conversation gracefully when it is unable to make sense of the end-user query. Accurately tagging a query as out-of-domain is particularly hard in scenarios when the chatbot is not equipped to handle a topic which has semantic overlap with an existing topic it is trained on. We propose a simple yet effective OOS detection method that outperforms standard OOS detection methods in a real-world deployment of virtual assistants. We discuss the various design and deployment considerations for a cloud platform solution to train virtual assistants and deploy them at scale. Additionally, we propose a collection of datasets that replicates real-world scenarios and show comprehensive results in various settings using both offline and online evaluation metrics.</abstract>
    <identifier type="citekey">qian-etal-2022-distinguish</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-industry.51</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-industry.51</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>502</start>
            <end>511</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants
%A Qian, Cheng
%A Qi, Haode
%A Wang, Gengyu
%A Kunc, Ladislav
%A Potdar, Saloni
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F qian-etal-2022-distinguish
%X Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a conversation gracefully when it is unable to make sense of the end-user query. Accurately tagging a query as out-of-domain is particularly hard in scenarios when the chatbot is not equipped to handle a topic which has semantic overlap with an existing topic it is trained on. We propose a simple yet effective OOS detection method that outperforms standard OOS detection methods in a real-world deployment of virtual assistants. We discuss the various design and deployment considerations for a cloud platform solution to train virtual assistants and deploy them at scale. Additionally, we propose a collection of datasets that replicates real-world scenarios and show comprehensive results in various settings using both offline and online evaluation metrics.
%R 10.18653/v1/2022.emnlp-industry.51
%U https://aclanthology.org/2022.emnlp-industry.51
%U https://doi.org/10.18653/v1/2022.emnlp-industry.51
%P 502-511

Markdown (Informal)

[Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants](https://aclanthology.org/2022.emnlp-industry.51) (Qian et al., EMNLP 2022)

• Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants (Qian et al., EMNLP 2022)

ACL

• Cheng Qian, Haode Qi, Gengyu Wang, Ladislav Kunc, and Saloni Potdar. 2022. Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 502–511, Abu Dhabi, UAE. Association for Computational Linguistics.