@inproceedings{sun-etal-2022-sportsinterview,
title = "{SPORTSINTERVIEW}: A Large-Scale Sports Interview Benchmark for Entity-centric Dialogues",
author = "Sun, Hanfei and
Cao, Ziyuan and
Yang, Diyi",
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-1.626",
pages = "5821--5828",
abstract = "We propose a novel knowledge grounded dialogue (interview) dataset SPORTSINTERVIEW set in the domain of sports interview. Our dataset contains two types of external knowledge sources as knowledge grounding, and is rich in content, containing about 150K interview sessions and 34K distinct interviewees. Compared to existing knowledge grounded dialogue datasets, our interview dataset is larger in size, comprises natural dialogues revolving around real-world sports matches, and have more than one dimension of external knowledge linking. We performed several experiments on SPORTSINTERVIEW and found that models such as BART fine-tuned on our dataset are able to learn lots of relevant domain knowledge and generate meaningful sentences (questions or responses). However, their performance is still far from humans (by comparing to gold sentences in the dataset) and hence encourages future research utilizing SPORTSINTERVIEW.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2022-sportsinterview">
<titleInfo>
<title>SPORTSINTERVIEW: A Large-Scale Sports Interview Benchmark for Entity-centric Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanfei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyuan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</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>We propose a novel knowledge grounded dialogue (interview) dataset SPORTSINTERVIEW set in the domain of sports interview. Our dataset contains two types of external knowledge sources as knowledge grounding, and is rich in content, containing about 150K interview sessions and 34K distinct interviewees. Compared to existing knowledge grounded dialogue datasets, our interview dataset is larger in size, comprises natural dialogues revolving around real-world sports matches, and have more than one dimension of external knowledge linking. We performed several experiments on SPORTSINTERVIEW and found that models such as BART fine-tuned on our dataset are able to learn lots of relevant domain knowledge and generate meaningful sentences (questions or responses). However, their performance is still far from humans (by comparing to gold sentences in the dataset) and hence encourages future research utilizing SPORTSINTERVIEW.</abstract>
<identifier type="citekey">sun-etal-2022-sportsinterview</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.626</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5821</start>
<end>5828</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPORTSINTERVIEW: A Large-Scale Sports Interview Benchmark for Entity-centric Dialogues
%A Sun, Hanfei
%A Cao, Ziyuan
%A Yang, Diyi
%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 sun-etal-2022-sportsinterview
%X We propose a novel knowledge grounded dialogue (interview) dataset SPORTSINTERVIEW set in the domain of sports interview. Our dataset contains two types of external knowledge sources as knowledge grounding, and is rich in content, containing about 150K interview sessions and 34K distinct interviewees. Compared to existing knowledge grounded dialogue datasets, our interview dataset is larger in size, comprises natural dialogues revolving around real-world sports matches, and have more than one dimension of external knowledge linking. We performed several experiments on SPORTSINTERVIEW and found that models such as BART fine-tuned on our dataset are able to learn lots of relevant domain knowledge and generate meaningful sentences (questions or responses). However, their performance is still far from humans (by comparing to gold sentences in the dataset) and hence encourages future research utilizing SPORTSINTERVIEW.
%U https://aclanthology.org/2022.lrec-1.626
%P 5821-5828
Markdown (Informal)
[SPORTSINTERVIEW: A Large-Scale Sports Interview Benchmark for Entity-centric Dialogues](https://aclanthology.org/2022.lrec-1.626) (Sun et al., LREC 2022)
ACL