@inproceedings{see-manning-2021-understanding,
title = "Understanding and predicting user dissatisfaction in a neural generative chatbot",
author = "See, Abigail and
Manning, Christopher",
editor = "Li, Haizhou and
Levow, Gina-Anne and
Yu, Zhou and
Gupta, Chitralekha and
Sisman, Berrak and
Cai, Siqi and
Vandyke, David and
Dethlefs, Nina and
Wu, Yan and
Li, Junyi Jessy",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.1",
doi = "10.18653/v1/2021.sigdial-1.1",
pages = "1--12",
abstract = "Neural generative dialogue agents have shown an increasing ability to hold short chitchat conversations, when evaluated by crowdworkers in controlled settings. However, their performance in real-life deployment {--} talking to intrinsically-motivated users in noisy environments {--} is less well-explored. In this paper, we perform a detailed case study of a neural generative model deployed as part of Chirpy Cardinal, an Alexa Prize socialbot. We find that unclear user utterances are a major source of generative errors such as ignoring, hallucination, unclearness and repetition. However, even in unambiguous contexts the model frequently makes reasoning errors. Though users express dissatisfaction in correlation with these errors, certain dissatisfaction types (such as offensiveness and privacy objections) depend on additional factors {--} such as the user{'}s personal attitudes, and prior unaddressed dissatisfaction in the conversation. Finally, we show that dissatisfied user utterances can be used as a semi-supervised learning signal to improve the dialogue system. We train a model to predict next-turn dissatisfaction, and show through human evaluation that as a ranking function, it selects higher-quality neural-generated utterances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="see-manning-2021-understanding">
<titleInfo>
<title>Understanding and predicting user dissatisfaction in a neural generative chatbot</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abigail</namePart>
<namePart type="family">See</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chitralekha</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrak</namePart>
<namePart type="family">Sisman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural generative dialogue agents have shown an increasing ability to hold short chitchat conversations, when evaluated by crowdworkers in controlled settings. However, their performance in real-life deployment – talking to intrinsically-motivated users in noisy environments – is less well-explored. In this paper, we perform a detailed case study of a neural generative model deployed as part of Chirpy Cardinal, an Alexa Prize socialbot. We find that unclear user utterances are a major source of generative errors such as ignoring, hallucination, unclearness and repetition. However, even in unambiguous contexts the model frequently makes reasoning errors. Though users express dissatisfaction in correlation with these errors, certain dissatisfaction types (such as offensiveness and privacy objections) depend on additional factors – such as the user’s personal attitudes, and prior unaddressed dissatisfaction in the conversation. Finally, we show that dissatisfied user utterances can be used as a semi-supervised learning signal to improve the dialogue system. We train a model to predict next-turn dissatisfaction, and show through human evaluation that as a ranking function, it selects higher-quality neural-generated utterances.</abstract>
<identifier type="citekey">see-manning-2021-understanding</identifier>
<identifier type="doi">10.18653/v1/2021.sigdial-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.1</url>
</location>
<part>
<date>2021-07</date>
<extent unit="page">
<start>1</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding and predicting user dissatisfaction in a neural generative chatbot
%A See, Abigail
%A Manning, Christopher
%Y Li, Haizhou
%Y Levow, Gina-Anne
%Y Yu, Zhou
%Y Gupta, Chitralekha
%Y Sisman, Berrak
%Y Cai, Siqi
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Wu, Yan
%Y Li, Junyi Jessy
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 July
%I Association for Computational Linguistics
%C Singapore and Online
%F see-manning-2021-understanding
%X Neural generative dialogue agents have shown an increasing ability to hold short chitchat conversations, when evaluated by crowdworkers in controlled settings. However, their performance in real-life deployment – talking to intrinsically-motivated users in noisy environments – is less well-explored. In this paper, we perform a detailed case study of a neural generative model deployed as part of Chirpy Cardinal, an Alexa Prize socialbot. We find that unclear user utterances are a major source of generative errors such as ignoring, hallucination, unclearness and repetition. However, even in unambiguous contexts the model frequently makes reasoning errors. Though users express dissatisfaction in correlation with these errors, certain dissatisfaction types (such as offensiveness and privacy objections) depend on additional factors – such as the user’s personal attitudes, and prior unaddressed dissatisfaction in the conversation. Finally, we show that dissatisfied user utterances can be used as a semi-supervised learning signal to improve the dialogue system. We train a model to predict next-turn dissatisfaction, and show through human evaluation that as a ranking function, it selects higher-quality neural-generated utterances.
%R 10.18653/v1/2021.sigdial-1.1
%U https://aclanthology.org/2021.sigdial-1.1
%U https://doi.org/10.18653/v1/2021.sigdial-1.1
%P 1-12
Markdown (Informal)
[Understanding and predicting user dissatisfaction in a neural generative chatbot](https://aclanthology.org/2021.sigdial-1.1) (See & Manning, SIGDIAL 2021)
ACL