@inproceedings{tong-etal-2022-docee,
title = "{D}oc{EE}: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction",
author = "Tong, MeiHan and
Xu, Bin and
Wang, Shuai and
Han, Meihuan and
Cao, Yixin and
Zhu, Jiangqi and
Chen, Siyu and
Hou, Lei and
Li, Juanzi",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.291",
doi = "10.18653/v1/2022.naacl-main.291",
pages = "3970--3982",
abstract = "Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentence-level event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major barrier to promote document-level event extraction has been the lack of large-scale and practical training and evaluation datasets. In this paper, we present DocEE, a new document-level event extraction dataset including 27,000+ events, 180,000+ arguments. We highlight three features: large-scale manual annotations, fine-grained argument types and application-oriented settings. Experiments show that there is still a big gap between state-of-the-art models and human beings (41{\%} Vs 85{\%} in F1 score), indicating that DocEE is an open issue. DocEE is now available at \url{https://github.com/tongmeihan1995/DocEE.git}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tong-etal-2022-docee">
<titleInfo>
<title>DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">MeiHan</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meihuan</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangqi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juanzi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentence-level event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major barrier to promote document-level event extraction has been the lack of large-scale and practical training and evaluation datasets. In this paper, we present DocEE, a new document-level event extraction dataset including 27,000+ events, 180,000+ arguments. We highlight three features: large-scale manual annotations, fine-grained argument types and application-oriented settings. Experiments show that there is still a big gap between state-of-the-art models and human beings (41% Vs 85% in F1 score), indicating that DocEE is an open issue. DocEE is now available at https://github.com/tongmeihan1995/DocEE.git.</abstract>
<identifier type="citekey">tong-etal-2022-docee</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.291</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.291</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3970</start>
<end>3982</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction
%A Tong, MeiHan
%A Xu, Bin
%A Wang, Shuai
%A Han, Meihuan
%A Cao, Yixin
%A Zhu, Jiangqi
%A Chen, Siyu
%A Hou, Lei
%A Li, Juanzi
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F tong-etal-2022-docee
%X Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentence-level event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major barrier to promote document-level event extraction has been the lack of large-scale and practical training and evaluation datasets. In this paper, we present DocEE, a new document-level event extraction dataset including 27,000+ events, 180,000+ arguments. We highlight three features: large-scale manual annotations, fine-grained argument types and application-oriented settings. Experiments show that there is still a big gap between state-of-the-art models and human beings (41% Vs 85% in F1 score), indicating that DocEE is an open issue. DocEE is now available at https://github.com/tongmeihan1995/DocEE.git.
%R 10.18653/v1/2022.naacl-main.291
%U https://aclanthology.org/2022.naacl-main.291
%U https://doi.org/10.18653/v1/2022.naacl-main.291
%P 3970-3982
Markdown (Informal)
[DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction](https://aclanthology.org/2022.naacl-main.291) (Tong et al., NAACL 2022)
ACL
- MeiHan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, and Juanzi Li. 2022. DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3970–3982, Seattle, United States. Association for Computational Linguistics.