@inproceedings{yang-tan-2026-segdre,
title = "{S}eg{DRE}: A Salient Entity Guided Approach to Document-Level Relation Extraction",
author = "Yang, Xing and
Tan, Chengxiang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1192/",
doi = "10.18653/v1/2026.findings-acl.1192",
pages = "23800--23812",
ISBN = "979-8-89176-395-1",
abstract = "In Document-level Relation Extraction (DocRE), relational facts are typically organized around a few salient entities. Explicitly capturing this topological structure is pivotal to addressing the two critical bottlenecks of the task: the extreme class imbalance and the complexity of multi-hop reasoning. Based on this insight, we first introduce the concept of the salient entity and propose a novel approach that decouples the extraction space into dense and sparse scenarios. Specifically, our approach restricts the search space for dense pairs to mitigate the dominance of the negative samples, and innovatively injects the rich semantic knowledge of salient entities to explicitly reconstruct the document for bridging disjoint evidence in multi-hop reasoning. Extensive experiments demonstrate that our approach yields consistent improvements over various backbone models and achieves advanced performance compared to existing enhancement methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-tan-2026-segdre">
<titleInfo>
<title>SegDRE: A Salient Entity Guided Approach to Document-Level Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengxiang</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>In Document-level Relation Extraction (DocRE), relational facts are typically organized around a few salient entities. Explicitly capturing this topological structure is pivotal to addressing the two critical bottlenecks of the task: the extreme class imbalance and the complexity of multi-hop reasoning. Based on this insight, we first introduce the concept of the salient entity and propose a novel approach that decouples the extraction space into dense and sparse scenarios. Specifically, our approach restricts the search space for dense pairs to mitigate the dominance of the negative samples, and innovatively injects the rich semantic knowledge of salient entities to explicitly reconstruct the document for bridging disjoint evidence in multi-hop reasoning. Extensive experiments demonstrate that our approach yields consistent improvements over various backbone models and achieves advanced performance compared to existing enhancement methods.</abstract>
<identifier type="citekey">yang-tan-2026-segdre</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1192</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1192/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>23800</start>
<end>23812</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SegDRE: A Salient Entity Guided Approach to Document-Level Relation Extraction
%A Yang, Xing
%A Tan, Chengxiang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F yang-tan-2026-segdre
%X In Document-level Relation Extraction (DocRE), relational facts are typically organized around a few salient entities. Explicitly capturing this topological structure is pivotal to addressing the two critical bottlenecks of the task: the extreme class imbalance and the complexity of multi-hop reasoning. Based on this insight, we first introduce the concept of the salient entity and propose a novel approach that decouples the extraction space into dense and sparse scenarios. Specifically, our approach restricts the search space for dense pairs to mitigate the dominance of the negative samples, and innovatively injects the rich semantic knowledge of salient entities to explicitly reconstruct the document for bridging disjoint evidence in multi-hop reasoning. Extensive experiments demonstrate that our approach yields consistent improvements over various backbone models and achieves advanced performance compared to existing enhancement methods.
%R 10.18653/v1/2026.findings-acl.1192
%U https://aclanthology.org/2026.findings-acl.1192/
%U https://doi.org/10.18653/v1/2026.findings-acl.1192
%P 23800-23812
Markdown (Informal)
[SegDRE: A Salient Entity Guided Approach to Document-Level Relation Extraction](https://aclanthology.org/2026.findings-acl.1192/) (Yang & Tan, Findings 2026)
ACL