@inproceedings{fang-etal-2026-drdee,
title = "{D}r{DEE}: A Deconstruction-Reconstruction Framework for Document-Level Event Extraction",
author = "Fang, Kuofei and
Wei, Yuting and
Wan, Zexuan and
Wang, Bo and
Wu, Siyan and
Wu, Bin",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1723/",
pages = "36857--36872",
ISBN = "979-8-89176-462-0",
abstract = "Document-level Event Extraction (DEE) aims to extract event records from given documents. Previous works typically process documents by constructing complex feature fusion matrices or graph structures, aiming to predict complete event records via entity selection or role filling. However, this holistic structure extraction paradigm often suffers from cascaded error propagation due to rigid entity dependency, multi-role structural omissions limited by selection mechanisms, and consequent scalability bottlenecks. In this paper, we propose a Deconstruction-Reconstruction Framework for Document-Level Event Extraction (DrDEE). This framework deconstructs the holistic event record extraction task into atomic Token-Event-Role (TER) triplet verification, and subsequently reconstructs event records from valid tokens. It realizes a paradigm shift in DEE from Many-to-Many Selection to One-to-One Verification, significantly simplifying the task formulation. Experimental results show that the proposed method outperforms state-of-the-art methods, confirming its effectiveness. Our code is available at https://anonymous.4open.science/r/DrDEE."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2026-drdee">
<titleInfo>
<title>DrDEE: A Deconstruction-Reconstruction Framework for Document-Level Event Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kuofei</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuting</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zexuan</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Document-level Event Extraction (DEE) aims to extract event records from given documents. Previous works typically process documents by constructing complex feature fusion matrices or graph structures, aiming to predict complete event records via entity selection or role filling. However, this holistic structure extraction paradigm often suffers from cascaded error propagation due to rigid entity dependency, multi-role structural omissions limited by selection mechanisms, and consequent scalability bottlenecks. In this paper, we propose a Deconstruction-Reconstruction Framework for Document-Level Event Extraction (DrDEE). This framework deconstructs the holistic event record extraction task into atomic Token-Event-Role (TER) triplet verification, and subsequently reconstructs event records from valid tokens. It realizes a paradigm shift in DEE from Many-to-Many Selection to One-to-One Verification, significantly simplifying the task formulation. Experimental results show that the proposed method outperforms state-of-the-art methods, confirming its effectiveness. Our code is available at https://anonymous.4open.science/r/DrDEE.</abstract>
<identifier type="citekey">fang-etal-2026-drdee</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1723/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>36857</start>
<end>36872</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DrDEE: A Deconstruction-Reconstruction Framework for Document-Level Event Extraction
%A Fang, Kuofei
%A Wei, Yuting
%A Wan, Zexuan
%A Wang, Bo
%A Wu, Siyan
%A Wu, Bin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F fang-etal-2026-drdee
%X Document-level Event Extraction (DEE) aims to extract event records from given documents. Previous works typically process documents by constructing complex feature fusion matrices or graph structures, aiming to predict complete event records via entity selection or role filling. However, this holistic structure extraction paradigm often suffers from cascaded error propagation due to rigid entity dependency, multi-role structural omissions limited by selection mechanisms, and consequent scalability bottlenecks. In this paper, we propose a Deconstruction-Reconstruction Framework for Document-Level Event Extraction (DrDEE). This framework deconstructs the holistic event record extraction task into atomic Token-Event-Role (TER) triplet verification, and subsequently reconstructs event records from valid tokens. It realizes a paradigm shift in DEE from Many-to-Many Selection to One-to-One Verification, significantly simplifying the task formulation. Experimental results show that the proposed method outperforms state-of-the-art methods, confirming its effectiveness. Our code is available at https://anonymous.4open.science/r/DrDEE.
%U https://aclanthology.org/2026.findings-emnlp.1723/
%P 36857-36872
Markdown (Informal)
[DrDEE: A Deconstruction-Reconstruction Framework for Document-Level Event Extraction](https://aclanthology.org/2026.findings-emnlp.1723/) (Fang et al., Findings 2026)
ACL