@inproceedings{pouran-ben-veyseh-etal-2022-behanceqa,
title = "{B}ehance{QA}: A New Dataset for Identifying Question-Answer Pairs in Video Transcripts",
author = "Pouran Ben Veyseh, Amir and
Lai, Viet and
Dernoncourt, Franck and
Nguyen, Thien",
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-1.796",
pages = "7321--7327",
abstract = "Question-Answer (QA) is one of the effective methods for storing knowledge which can be used for future retrieval. As such, identifying mentions of questions and their answers in text is necessary for a knowledge construction and retrieval systems. In the literature, QA identification has been well studied in the NLP community. However, most of the prior works are restricted to formal written documents such as papers or websites. As such, Questions and Answers that are presented in informal/noisy documents have not been adequately studied. One of the domains that can significantly benefit from QA identification is the domain of livestreaming video transcripts that involve abundant QA pairs to provide valuable knowledge for future users and services. Since video transcripts are often transcribed automatically for scale, they are prone to errors. Combined with the informal nature of discussion in a video, prior QA identification systems might not be able to perform well in this domain. To enable comprehensive research in this domain, we present a large-scale QA identification dataset annotated by human over transcripts of 500 hours of streamed videos. We employ Behance.net to collect the videos and their automatically obtained transcripts. Furthermore, we conduct extensive analysis on the annotated dataset to understand the complexity of QA identification for livestreaming video transcripts. Our experiments show that the annotated dataset presents unique challenges for existing methods and more research is necessary to explore more effective methods. The dataset and the models developed in this work will be publicly released for future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pouran-ben-veyseh-etal-2022-behanceqa">
<titleInfo>
<title>BehanceQA: A New Dataset for Identifying Question-Answer Pairs in Video Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Pouran Ben Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="family">Nguyen</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>Question-Answer (QA) is one of the effective methods for storing knowledge which can be used for future retrieval. As such, identifying mentions of questions and their answers in text is necessary for a knowledge construction and retrieval systems. In the literature, QA identification has been well studied in the NLP community. However, most of the prior works are restricted to formal written documents such as papers or websites. As such, Questions and Answers that are presented in informal/noisy documents have not been adequately studied. One of the domains that can significantly benefit from QA identification is the domain of livestreaming video transcripts that involve abundant QA pairs to provide valuable knowledge for future users and services. Since video transcripts are often transcribed automatically for scale, they are prone to errors. Combined with the informal nature of discussion in a video, prior QA identification systems might not be able to perform well in this domain. To enable comprehensive research in this domain, we present a large-scale QA identification dataset annotated by human over transcripts of 500 hours of streamed videos. We employ Behance.net to collect the videos and their automatically obtained transcripts. Furthermore, we conduct extensive analysis on the annotated dataset to understand the complexity of QA identification for livestreaming video transcripts. Our experiments show that the annotated dataset presents unique challenges for existing methods and more research is necessary to explore more effective methods. The dataset and the models developed in this work will be publicly released for future research.</abstract>
<identifier type="citekey">pouran-ben-veyseh-etal-2022-behanceqa</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.796</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7321</start>
<end>7327</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BehanceQA: A New Dataset for Identifying Question-Answer Pairs in Video Transcripts
%A Pouran Ben Veyseh, Amir
%A Lai, Viet
%A Dernoncourt, Franck
%A Nguyen, Thien
%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 pouran-ben-veyseh-etal-2022-behanceqa
%X Question-Answer (QA) is one of the effective methods for storing knowledge which can be used for future retrieval. As such, identifying mentions of questions and their answers in text is necessary for a knowledge construction and retrieval systems. In the literature, QA identification has been well studied in the NLP community. However, most of the prior works are restricted to formal written documents such as papers or websites. As such, Questions and Answers that are presented in informal/noisy documents have not been adequately studied. One of the domains that can significantly benefit from QA identification is the domain of livestreaming video transcripts that involve abundant QA pairs to provide valuable knowledge for future users and services. Since video transcripts are often transcribed automatically for scale, they are prone to errors. Combined with the informal nature of discussion in a video, prior QA identification systems might not be able to perform well in this domain. To enable comprehensive research in this domain, we present a large-scale QA identification dataset annotated by human over transcripts of 500 hours of streamed videos. We employ Behance.net to collect the videos and their automatically obtained transcripts. Furthermore, we conduct extensive analysis on the annotated dataset to understand the complexity of QA identification for livestreaming video transcripts. Our experiments show that the annotated dataset presents unique challenges for existing methods and more research is necessary to explore more effective methods. The dataset and the models developed in this work will be publicly released for future research.
%U https://aclanthology.org/2022.lrec-1.796
%P 7321-7327
Markdown (Informal)
[BehanceQA: A New Dataset for Identifying Question-Answer Pairs in Video Transcripts](https://aclanthology.org/2022.lrec-1.796) (Pouran Ben Veyseh et al., LREC 2022)
ACL