@article{komatani-etal-2022-user,
title = "User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues",
author = "Komatani, Kazunori and
Ono, Kohei and
Takeda, Ryu and
Nichols, Eric and
Nakano, Mikio",
editor = "Stent, Amanda and
Eugenio, Barbara Di and
Poesio, Massimo and
Georgila, Kallirroi and
Stede, Manfred",
journal = "Dialogue {\&} Discourse",
volume = "13",
month = jun,
year = "2022",
address = "Chicago, Illinois, USA",
publisher = "University of Illinois Chicago",
url = "https://aclanthology.org/2022.dnd-13.4/",
doi = "10.5210/dad.2022.104",
pages = "96--122",
abstract = "We have been addressing the problem of acquiring attributes of unknown terms through dialogues and previously proposed an approach using the implicit confirmation process. It is crucial for dialogue systems to ask questions that do not diminish the user{'}s willingness to talk. In this paper, we conducted a user study to investigate user impression for several question types, including explicit and implicit, to acquire lexical knowledge. We clarified the order among the types and found that repeating the same question type annoys the user and degrades user impression even when the content of the questions is correct. We also propose a method for determining whether an estimated attribute is correct, which is included in an implicit question. The method exploits multiple-user responses to implicit questions about the attribute of the same unknown term. Experimental results revealed that the proposed method exhibited a higher precision rate for determining the correctly estimated attributes than when only single-user responses were considered."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="komatani-etal-2022-user">
<titleInfo>
<title>User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kohei</namePart>
<namePart type="family">Ono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryu</namePart>
<namePart type="family">Takeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Nichols</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Dialogue & Discourse</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>University of Illinois Chicago</publisher>
<place>
<placeTerm type="text">Chicago, Illinois, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We have been addressing the problem of acquiring attributes of unknown terms through dialogues and previously proposed an approach using the implicit confirmation process. It is crucial for dialogue systems to ask questions that do not diminish the user’s willingness to talk. In this paper, we conducted a user study to investigate user impression for several question types, including explicit and implicit, to acquire lexical knowledge. We clarified the order among the types and found that repeating the same question type annoys the user and degrades user impression even when the content of the questions is correct. We also propose a method for determining whether an estimated attribute is correct, which is included in an implicit question. The method exploits multiple-user responses to implicit questions about the attribute of the same unknown term. Experimental results revealed that the proposed method exhibited a higher precision rate for determining the correctly estimated attributes than when only single-user responses were considered.</abstract>
<identifier type="citekey">komatani-etal-2022-user</identifier>
<identifier type="doi">10.5210/dad.2022.104</identifier>
<location>
<url>https://aclanthology.org/2022.dnd-13.4/</url>
</location>
<part>
<date>2022-06</date>
<detail type="volume"><number>13</number></detail>
<extent unit="page">
<start>96</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues
%A Komatani, Kazunori
%A Ono, Kohei
%A Takeda, Ryu
%A Nichols, Eric
%A Nakano, Mikio
%J Dialogue & Discourse
%D 2022
%8 June
%V 13
%I University of Illinois Chicago
%C Chicago, Illinois, USA
%F komatani-etal-2022-user
%X We have been addressing the problem of acquiring attributes of unknown terms through dialogues and previously proposed an approach using the implicit confirmation process. It is crucial for dialogue systems to ask questions that do not diminish the user’s willingness to talk. In this paper, we conducted a user study to investigate user impression for several question types, including explicit and implicit, to acquire lexical knowledge. We clarified the order among the types and found that repeating the same question type annoys the user and degrades user impression even when the content of the questions is correct. We also propose a method for determining whether an estimated attribute is correct, which is included in an implicit question. The method exploits multiple-user responses to implicit questions about the attribute of the same unknown term. Experimental results revealed that the proposed method exhibited a higher precision rate for determining the correctly estimated attributes than when only single-user responses were considered.
%R 10.5210/dad.2022.104
%U https://aclanthology.org/2022.dnd-13.4/
%U https://doi.org/10.5210/dad.2022.104
%P 96-122
Markdown (Informal)
[User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues](https://aclanthology.org/2022.dnd-13.4/) (Komatani et al., DND 2022)
ACL