@inproceedings{chierici-etal-2020-margarita,
title = "The Margarita Dialogue Corpus: A Data Set for Time-Offset Interactions and Unstructured Dialogue Systems",
author = "Chierici, Alberto and
Habash, Nizar and
Bicec, Margarita",
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-1.60",
pages = "476--484",
abstract = "Time-Offset Interaction Applications (TOIAs) are systems that simulate face-to-face conversations between humans and digital human avatars recorded in the past. Developing a well-functioning TOIA involves several research areas: artificial intelligence, human-computer interaction, natural language processing, question answering, and dialogue systems. The first challenges are to define a sensible methodology for data collection and to create useful data sets for training the system to retrieve the best answer to a user{'}s question. In this paper, we present three main contributions: a methodology for creating the knowledge base for a TOIA, a dialogue corpus, and baselines for single-turn answer retrieval. We develop the methodology using a two-step strategy. First, we let the avatar maker list pairs by intuition, guessing what possible questions a user may ask to the avatar. Second, we record actual dialogues between random individuals and the avatar-maker. We make the Margarita Dialogue Corpus available to the research community. This corpus comprises the knowledge base in text format, the video clips for each answer, and the annotated dialogues.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chierici-etal-2020-margarita">
<titleInfo>
<title>The Margarita Dialogue Corpus: A Data Set for Time-Offset Interactions and Unstructured Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Chierici</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margarita</namePart>
<namePart type="family">Bicec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">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>Time-Offset Interaction Applications (TOIAs) are systems that simulate face-to-face conversations between humans and digital human avatars recorded in the past. Developing a well-functioning TOIA involves several research areas: artificial intelligence, human-computer interaction, natural language processing, question answering, and dialogue systems. The first challenges are to define a sensible methodology for data collection and to create useful data sets for training the system to retrieve the best answer to a user’s question. In this paper, we present three main contributions: a methodology for creating the knowledge base for a TOIA, a dialogue corpus, and baselines for single-turn answer retrieval. We develop the methodology using a two-step strategy. First, we let the avatar maker list pairs by intuition, guessing what possible questions a user may ask to the avatar. Second, we record actual dialogues between random individuals and the avatar-maker. We make the Margarita Dialogue Corpus available to the research community. This corpus comprises the knowledge base in text format, the video clips for each answer, and the annotated dialogues.</abstract>
<identifier type="citekey">chierici-etal-2020-margarita</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.60</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>476</start>
<end>484</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Margarita Dialogue Corpus: A Data Set for Time-Offset Interactions and Unstructured Dialogue Systems
%A Chierici, Alberto
%A Habash, Nizar
%A Bicec, Margarita
%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 English
%F chierici-etal-2020-margarita
%X Time-Offset Interaction Applications (TOIAs) are systems that simulate face-to-face conversations between humans and digital human avatars recorded in the past. Developing a well-functioning TOIA involves several research areas: artificial intelligence, human-computer interaction, natural language processing, question answering, and dialogue systems. The first challenges are to define a sensible methodology for data collection and to create useful data sets for training the system to retrieve the best answer to a user’s question. In this paper, we present three main contributions: a methodology for creating the knowledge base for a TOIA, a dialogue corpus, and baselines for single-turn answer retrieval. We develop the methodology using a two-step strategy. First, we let the avatar maker list pairs by intuition, guessing what possible questions a user may ask to the avatar. Second, we record actual dialogues between random individuals and the avatar-maker. We make the Margarita Dialogue Corpus available to the research community. This corpus comprises the knowledge base in text format, the video clips for each answer, and the annotated dialogues.
%U https://aclanthology.org/2020.lrec-1.60
%P 476-484
Markdown (Informal)
[The Margarita Dialogue Corpus: A Data Set for Time-Offset Interactions and Unstructured Dialogue Systems](https://aclanthology.org/2020.lrec-1.60) (Chierici et al., LREC 2020)
ACL