@inproceedings{hayashibe-2022-self,
title = "Self-Contained Utterance Description Corpus for {J}apanese Dialog",
author = "Hayashibe, Yuta",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.133",
pages = "1249--1255",
abstract = "Often both an utterance and its context must be read to understand its intent in a dialog. Herein we propose a task, Self- Contained Utterance Description (SCUD), to describe the intent of an utterance in a dialog with multiple simple natural sentences without the context. If a task can be performed concurrently with high accuracy as the conversation continues such as in an accommodation search dialog, the operator can easily suggest candidates to the customer by inputting SCUDs of the customer{'}s utterances to the accommodation search system. SCUDs can also describe the transition of customer requests from the dialog log. We construct a Japanese corpus to train and evaluate automatic SCUD generation. The corpus consists of 210 dialogs containing 10,814 sentences. We conduct an experiment to verify that SCUDs can be automatically generated. Additionally, we investigate the influence of the amount of training data on the automatic generation performance using 8,200 additional examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayashibe-2022-self">
<titleInfo>
<title>Self-Contained Utterance Description Corpus for Japanese Dialog</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Hayashibe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>Often both an utterance and its context must be read to understand its intent in a dialog. Herein we propose a task, Self- Contained Utterance Description (SCUD), to describe the intent of an utterance in a dialog with multiple simple natural sentences without the context. If a task can be performed concurrently with high accuracy as the conversation continues such as in an accommodation search dialog, the operator can easily suggest candidates to the customer by inputting SCUDs of the customer’s utterances to the accommodation search system. SCUDs can also describe the transition of customer requests from the dialog log. We construct a Japanese corpus to train and evaluate automatic SCUD generation. The corpus consists of 210 dialogs containing 10,814 sentences. We conduct an experiment to verify that SCUDs can be automatically generated. Additionally, we investigate the influence of the amount of training data on the automatic generation performance using 8,200 additional examples.</abstract>
<identifier type="citekey">hayashibe-2022-self</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.133</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1249</start>
<end>1255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Contained Utterance Description Corpus for Japanese Dialog
%A Hayashibe, Yuta
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F hayashibe-2022-self
%X Often both an utterance and its context must be read to understand its intent in a dialog. Herein we propose a task, Self- Contained Utterance Description (SCUD), to describe the intent of an utterance in a dialog with multiple simple natural sentences without the context. If a task can be performed concurrently with high accuracy as the conversation continues such as in an accommodation search dialog, the operator can easily suggest candidates to the customer by inputting SCUDs of the customer’s utterances to the accommodation search system. SCUDs can also describe the transition of customer requests from the dialog log. We construct a Japanese corpus to train and evaluate automatic SCUD generation. The corpus consists of 210 dialogs containing 10,814 sentences. We conduct an experiment to verify that SCUDs can be automatically generated. Additionally, we investigate the influence of the amount of training data on the automatic generation performance using 8,200 additional examples.
%U https://aclanthology.org/2022.lrec-1.133
%P 1249-1255
Markdown (Informal)
[Self-Contained Utterance Description Corpus for Japanese Dialog](https://aclanthology.org/2022.lrec-1.133) (Hayashibe, LREC 2022)
ACL