@inproceedings{chen-etal-2021-joint-multimedia-event,
title = "Joint Multimedia Event Extraction from Video and Article",
author = "Chen, Brian and
Lin, Xudong and
Thomas, Christopher and
Li, Manling and
Yoshida, Shoya and
Chum, Lovish and
Ji, Heng and
Chang, Shih-Fu",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.8",
doi = "10.18653/v1/2021.findings-emnlp.8",
pages = "74--88",
abstract = "Visual and textual modalities contribute complementary information about events described in multimedia documents. Videos contain rich dynamics and detailed unfoldings of events, while text describes more high-level and abstract concepts. However, existing event extraction methods either do not handle video or solely target video while ignoring other modalities. In contrast, we propose the first approach to jointly extract events from both video and text articles. We introduce the new task of Video MultiMedia Event Extraction and propose two novel components to build the first system towards this task. First, we propose the first self-supervised cross-modal event coreference model that can determine coreference between video events and text events without any manually annotated pairs. Second, we introduce the first cross-modal transformer architecture, which extracts structured event information from both videos and text documents. We also construct and will publicly release a new benchmark of video-article pairs, consisting of 860 video-article pairs with extensive annotations for evaluating methods on this task. Our experimental results demonstrate the effectiveness of our proposed method on our new benchmark dataset. We achieve 6.0{\%} and 5.8{\%} absolute F-score gain on multimodal event coreference resolution and multimedia event extraction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2021-joint-multimedia-event">
<titleInfo>
<title>Joint Multimedia Event Extraction from Video and Article</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoya</namePart>
<namePart type="family">Yoshida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lovish</namePart>
<namePart type="family">Chum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shih-Fu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual and textual modalities contribute complementary information about events described in multimedia documents. Videos contain rich dynamics and detailed unfoldings of events, while text describes more high-level and abstract concepts. However, existing event extraction methods either do not handle video or solely target video while ignoring other modalities. In contrast, we propose the first approach to jointly extract events from both video and text articles. We introduce the new task of Video MultiMedia Event Extraction and propose two novel components to build the first system towards this task. First, we propose the first self-supervised cross-modal event coreference model that can determine coreference between video events and text events without any manually annotated pairs. Second, we introduce the first cross-modal transformer architecture, which extracts structured event information from both videos and text documents. We also construct and will publicly release a new benchmark of video-article pairs, consisting of 860 video-article pairs with extensive annotations for evaluating methods on this task. Our experimental results demonstrate the effectiveness of our proposed method on our new benchmark dataset. We achieve 6.0% and 5.8% absolute F-score gain on multimodal event coreference resolution and multimedia event extraction.</abstract>
<identifier type="citekey">chen-etal-2021-joint-multimedia-event</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.8</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.8</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>74</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Multimedia Event Extraction from Video and Article
%A Chen, Brian
%A Lin, Xudong
%A Thomas, Christopher
%A Li, Manling
%A Yoshida, Shoya
%A Chum, Lovish
%A Ji, Heng
%A Chang, Shih-Fu
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F chen-etal-2021-joint-multimedia-event
%X Visual and textual modalities contribute complementary information about events described in multimedia documents. Videos contain rich dynamics and detailed unfoldings of events, while text describes more high-level and abstract concepts. However, existing event extraction methods either do not handle video or solely target video while ignoring other modalities. In contrast, we propose the first approach to jointly extract events from both video and text articles. We introduce the new task of Video MultiMedia Event Extraction and propose two novel components to build the first system towards this task. First, we propose the first self-supervised cross-modal event coreference model that can determine coreference between video events and text events without any manually annotated pairs. Second, we introduce the first cross-modal transformer architecture, which extracts structured event information from both videos and text documents. We also construct and will publicly release a new benchmark of video-article pairs, consisting of 860 video-article pairs with extensive annotations for evaluating methods on this task. Our experimental results demonstrate the effectiveness of our proposed method on our new benchmark dataset. We achieve 6.0% and 5.8% absolute F-score gain on multimodal event coreference resolution and multimedia event extraction.
%R 10.18653/v1/2021.findings-emnlp.8
%U https://aclanthology.org/2021.findings-emnlp.8
%U https://doi.org/10.18653/v1/2021.findings-emnlp.8
%P 74-88
Markdown (Informal)
[Joint Multimedia Event Extraction from Video and Article](https://aclanthology.org/2021.findings-emnlp.8) (Chen et al., Findings 2021)
ACL
- Brian Chen, Xudong Lin, Christopher Thomas, Manling Li, Shoya Yoshida, Lovish Chum, Heng Ji, and Shih-Fu Chang. 2021. Joint Multimedia Event Extraction from Video and Article. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 74–88, Punta Cana, Dominican Republic. Association for Computational Linguistics.