<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akasaki-sassano-2024-detecting">
    <titleInfo>
        <title>Detecting Ambiguous Utterances in an Intelligent Assistant</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Satoshi</namePart>
        <namePart type="family">Akasaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manabu</namePart>
        <namePart type="family">Sassano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Franck</namePart>
            <namePart type="family">Dernoncourt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Preoţiuc-Pietro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anastasia</namePart>
            <namePart type="family">Shimorina</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, US</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In intelligent assistants that perform both chatting and tasks through dialogue, like Siri and Alexa, users often make ambiguous utterances such as “I’m hungry” or “I have a headache,” which can be interpreted as either chat or task intents. Naively determining these intents can lead to mismatched responses, spoiling the user experience. Therefore, it is desirable to determine the ambiguity of user utterances. We created a dataset from an actual intelligent assistant via crowdsourcing and analyzed tendencies of ambiguous utterances. Using this labeled data of chat, task, and ambiguous intents, we developed a supervised intent classification model. To detect ambiguous utterances robustly, we propose feeding sentence embeddings developed from microblogs and search logs with a self-attention mechanism. Experiments showed that our model outperformed two baselines, including a strong LLM-based one. We will release the dataset.</abstract>
    <identifier type="citekey">akasaki-sassano-2024-detecting</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-industry.28</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>386</start>
            <end>394</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Detecting Ambiguous Utterances in an Intelligent Assistant
%A Akasaki, Satoshi
%A Sassano, Manabu
%Y Dernoncourt, Franck
%Y Preoţiuc-Pietro, Daniel
%Y Shimorina, Anastasia
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F akasaki-sassano-2024-detecting
%X In intelligent assistants that perform both chatting and tasks through dialogue, like Siri and Alexa, users often make ambiguous utterances such as “I’m hungry” or “I have a headache,” which can be interpreted as either chat or task intents. Naively determining these intents can lead to mismatched responses, spoiling the user experience. Therefore, it is desirable to determine the ambiguity of user utterances. We created a dataset from an actual intelligent assistant via crowdsourcing and analyzed tendencies of ambiguous utterances. Using this labeled data of chat, task, and ambiguous intents, we developed a supervised intent classification model. To detect ambiguous utterances robustly, we propose feeding sentence embeddings developed from microblogs and search logs with a self-attention mechanism. Experiments showed that our model outperformed two baselines, including a strong LLM-based one. We will release the dataset.
%U https://aclanthology.org/2024.emnlp-industry.28
%P 386-394

Markdown (Informal)

[Detecting Ambiguous Utterances in an Intelligent Assistant](https://aclanthology.org/2024.emnlp-industry.28) (Akasaki & Sassano, EMNLP 2024)

• Detecting Ambiguous Utterances in an Intelligent Assistant (Akasaki & Sassano, EMNLP 2024)

ACL

• Satoshi Akasaki and Manabu Sassano. 2024. Detecting Ambiguous Utterances in an Intelligent Assistant. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 386–394, Miami, Florida, US. Association for Computational Linguistics.