@inproceedings{veyseh-etal-2022-event,
title = "Event Extraction in Video Transcripts",
author = "Veyseh, Amir Pouran Ben and
Lai, Viet Dac and
Dernoncourt, Franck and
Nguyen, Thien Huu",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.625",
pages = "7156--7165",
abstract = "Event extraction (EE) is one of the fundamental tasks for information extraction whose goal is to identify mentions of events and their participants in text. Due to its importance, different methods and datasets have been introduced for EE. However, existing EE datasets are limited to formally written documents such as news articles or scientific papers. As such, the challenges of EE in informal and noisy texts are not adequately studied. In particular, video transcripts constitute an important domain that can benefit tremendously from EE systems (e.g., video retrieval), but has not been studied in EE literature due to the lack of necessary datasets. To address this limitation, we propose the first large-scale EE dataset obtained for transcripts of streamed videos on the video hosting platform Behance to promote future research in this area. In addition, we extensively evaluate existing state-of-the-art EE methods on our new dataset. We demonstrate that such systems cannot achieve adequate performance on the proposed dataset, revealing challenges and opportunities for further research effort.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="veyseh-etal-2022-event">
<titleInfo>
<title>Event Extraction in Video Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="given">Pouran</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="given">Dac</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="given">Huu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Event extraction (EE) is one of the fundamental tasks for information extraction whose goal is to identify mentions of events and their participants in text. Due to its importance, different methods and datasets have been introduced for EE. However, existing EE datasets are limited to formally written documents such as news articles or scientific papers. As such, the challenges of EE in informal and noisy texts are not adequately studied. In particular, video transcripts constitute an important domain that can benefit tremendously from EE systems (e.g., video retrieval), but has not been studied in EE literature due to the lack of necessary datasets. To address this limitation, we propose the first large-scale EE dataset obtained for transcripts of streamed videos on the video hosting platform Behance to promote future research in this area. In addition, we extensively evaluate existing state-of-the-art EE methods on our new dataset. We demonstrate that such systems cannot achieve adequate performance on the proposed dataset, revealing challenges and opportunities for further research effort.</abstract>
<identifier type="citekey">veyseh-etal-2022-event</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.625</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>7156</start>
<end>7165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Event Extraction in Video Transcripts
%A Veyseh, Amir Pouran Ben
%A Lai, Viet Dac
%A Dernoncourt, Franck
%A Nguyen, Thien Huu
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F veyseh-etal-2022-event
%X Event extraction (EE) is one of the fundamental tasks for information extraction whose goal is to identify mentions of events and their participants in text. Due to its importance, different methods and datasets have been introduced for EE. However, existing EE datasets are limited to formally written documents such as news articles or scientific papers. As such, the challenges of EE in informal and noisy texts are not adequately studied. In particular, video transcripts constitute an important domain that can benefit tremendously from EE systems (e.g., video retrieval), but has not been studied in EE literature due to the lack of necessary datasets. To address this limitation, we propose the first large-scale EE dataset obtained for transcripts of streamed videos on the video hosting platform Behance to promote future research in this area. In addition, we extensively evaluate existing state-of-the-art EE methods on our new dataset. We demonstrate that such systems cannot achieve adequate performance on the proposed dataset, revealing challenges and opportunities for further research effort.
%U https://aclanthology.org/2022.coling-1.625
%P 7156-7165
Markdown (Informal)
[Event Extraction in Video Transcripts](https://aclanthology.org/2022.coling-1.625) (Veyseh et al., COLING 2022)
ACL
- Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt, and Thien Huu Nguyen. 2022. Event Extraction in Video Transcripts. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7156–7165, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.