@inproceedings{asao-etal-2020-understanding,
title = "Understanding User Utterances in a Dialog System for Caregiving",
author = "Asao, Yoshihiko and
Kloetzer, Julien and
Mizuno, Junta and
Saiki, Dai and
Kadowaki, Kazuma and
Torisawa, Kentaro",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.82/",
pages = "653--661",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "A dialog system that can monitor the health status of seniors has a huge potential for solving the labor force shortage in the caregiving industry in aging societies. As a part of efforts to create such a system, we are developing two modules that are aimed to correctly interpret user utterances: (i) a yes/no response classifier, which categorizes responses to health-related yes/no questions that the system asks; and (ii) an entailment recognizer, which detects users' voluntary mentions about their health status. To apply machine learning approaches to the development of the modules, we created large annotated datasets of 280,467 question-response pairs and 38,868 voluntary utterances. For question-response pairs, we asked annotators to avoid direct {\textquotedblleft}yes{\textquotedblright} or {\textquotedblleft}no{\textquotedblright} answers, so that our data could cover a wide range of possible natural language responses. The two modules were implemented by fine-tuning a BERT model, which is a recent successful neural network model. For the yes/no response classifier, the macro-average of the average precisions (APs) over all of our four categories (Yes/No/Unknown/Other) was 82.6{\%} (96.3{\%} for {\textquotedblleft}yes{\textquotedblright} responses and 91.8{\%} for {\textquotedblleft}no{\textquotedblright} responses), while for the entailment recognizer it was 89.9{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asao-etal-2020-understanding">
<titleInfo>
<title>Understanding User Utterances in a Dialog System for Caregiving</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoshihiko</namePart>
<namePart type="family">Asao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Kloetzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junta</namePart>
<namePart type="family">Mizuno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dai</namePart>
<namePart type="family">Saiki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuma</namePart>
<namePart type="family">Kadowaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Torisawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>A dialog system that can monitor the health status of seniors has a huge potential for solving the labor force shortage in the caregiving industry in aging societies. As a part of efforts to create such a system, we are developing two modules that are aimed to correctly interpret user utterances: (i) a yes/no response classifier, which categorizes responses to health-related yes/no questions that the system asks; and (ii) an entailment recognizer, which detects users’ voluntary mentions about their health status. To apply machine learning approaches to the development of the modules, we created large annotated datasets of 280,467 question-response pairs and 38,868 voluntary utterances. For question-response pairs, we asked annotators to avoid direct “yes” or “no” answers, so that our data could cover a wide range of possible natural language responses. The two modules were implemented by fine-tuning a BERT model, which is a recent successful neural network model. For the yes/no response classifier, the macro-average of the average precisions (APs) over all of our four categories (Yes/No/Unknown/Other) was 82.6% (96.3% for “yes” responses and 91.8% for “no” responses), while for the entailment recognizer it was 89.9%.</abstract>
<identifier type="citekey">asao-etal-2020-understanding</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.82/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>653</start>
<end>661</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding User Utterances in a Dialog System for Caregiving
%A Asao, Yoshihiko
%A Kloetzer, Julien
%A Mizuno, Junta
%A Saiki, Dai
%A Kadowaki, Kazuma
%A Torisawa, Kentaro
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F asao-etal-2020-understanding
%X A dialog system that can monitor the health status of seniors has a huge potential for solving the labor force shortage in the caregiving industry in aging societies. As a part of efforts to create such a system, we are developing two modules that are aimed to correctly interpret user utterances: (i) a yes/no response classifier, which categorizes responses to health-related yes/no questions that the system asks; and (ii) an entailment recognizer, which detects users’ voluntary mentions about their health status. To apply machine learning approaches to the development of the modules, we created large annotated datasets of 280,467 question-response pairs and 38,868 voluntary utterances. For question-response pairs, we asked annotators to avoid direct “yes” or “no” answers, so that our data could cover a wide range of possible natural language responses. The two modules were implemented by fine-tuning a BERT model, which is a recent successful neural network model. For the yes/no response classifier, the macro-average of the average precisions (APs) over all of our four categories (Yes/No/Unknown/Other) was 82.6% (96.3% for “yes” responses and 91.8% for “no” responses), while for the entailment recognizer it was 89.9%.
%U https://aclanthology.org/2020.lrec-1.82/
%P 653-661
Markdown (Informal)
[Understanding User Utterances in a Dialog System for Caregiving](https://aclanthology.org/2020.lrec-1.82/) (Asao et al., LREC 2020)
ACL
- Yoshihiko Asao, Julien Kloetzer, Junta Mizuno, Dai Saiki, Kazuma Kadowaki, and Kentaro Torisawa. 2020. Understanding User Utterances in a Dialog System for Caregiving. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 653–661, Marseille, France. European Language Resources Association.