@inproceedings{ren-etal-2024-deie-benchmarking,
title = "{DEIE}: Benchmarking Document-level Event Information Extraction with a Large-scale {C}hinese News Dataset",
author = "Ren, Yubing and
Cao, Yanan and
Li, Hao and
Li, Yingjie and
Ma, Zixuan ZM and
Fang, Fang and
Guo, Ping and
Ma, Wei",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.410",
pages = "4592--4604",
abstract = "A text corpus centered on events is foundational to research concerning the detection, representation, reasoning, and harnessing of online events. The majority of current event-based datasets mainly target sentence-level tasks, thus to advance event-related research spanning from sentence to document level, this paper introduces DEIE, a unified large-scale document-level event information extraction dataset with over 56,000+ events and 242,000+ arguments. Three key features stand out: large-scale manual annotation (20,000 documents), comprehensive unified annotation (encompassing event trigger/argument, summary, and relation at once), and emergency events annotation (covering 19 emergency types). Notably, our experiments reveal that current event-related models struggle with DEIE, signaling a pressing need for more advanced event-related research in the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2024-deie-benchmarking">
<titleInfo>
<title>DEIE: Benchmarking Document-level Event Information Extraction with a Large-scale Chinese News Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yubing</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixuan</namePart>
<namePart type="given">ZM</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A text corpus centered on events is foundational to research concerning the detection, representation, reasoning, and harnessing of online events. The majority of current event-based datasets mainly target sentence-level tasks, thus to advance event-related research spanning from sentence to document level, this paper introduces DEIE, a unified large-scale document-level event information extraction dataset with over 56,000+ events and 242,000+ arguments. Three key features stand out: large-scale manual annotation (20,000 documents), comprehensive unified annotation (encompassing event trigger/argument, summary, and relation at once), and emergency events annotation (covering 19 emergency types). Notably, our experiments reveal that current event-related models struggle with DEIE, signaling a pressing need for more advanced event-related research in the future.</abstract>
<identifier type="citekey">ren-etal-2024-deie-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.410</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4592</start>
<end>4604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DEIE: Benchmarking Document-level Event Information Extraction with a Large-scale Chinese News Dataset
%A Ren, Yubing
%A Cao, Yanan
%A Li, Hao
%A Li, Yingjie
%A Ma, Zixuan ZM
%A Fang, Fang
%A Guo, Ping
%A Ma, Wei
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ren-etal-2024-deie-benchmarking
%X A text corpus centered on events is foundational to research concerning the detection, representation, reasoning, and harnessing of online events. The majority of current event-based datasets mainly target sentence-level tasks, thus to advance event-related research spanning from sentence to document level, this paper introduces DEIE, a unified large-scale document-level event information extraction dataset with over 56,000+ events and 242,000+ arguments. Three key features stand out: large-scale manual annotation (20,000 documents), comprehensive unified annotation (encompassing event trigger/argument, summary, and relation at once), and emergency events annotation (covering 19 emergency types). Notably, our experiments reveal that current event-related models struggle with DEIE, signaling a pressing need for more advanced event-related research in the future.
%U https://aclanthology.org/2024.lrec-main.410
%P 4592-4604
Markdown (Informal)
[DEIE: Benchmarking Document-level Event Information Extraction with a Large-scale Chinese News Dataset](https://aclanthology.org/2024.lrec-main.410) (Ren et al., LREC-COLING 2024)
ACL
- Yubing Ren, Yanan Cao, Hao Li, Yingjie Li, Zixuan ZM Ma, Fang Fang, Ping Guo, and Wei Ma. 2024. DEIE: Benchmarking Document-level Event Information Extraction with a Large-scale Chinese News Dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4592–4604, Torino, Italia. ELRA and ICCL.