@inproceedings{wang-etal-2026-atsr,
title = "{ATSR}: Adaptive Template Selection and Role-Aware Routing for Document-Level Multi-Event Argument Extraction",
author = "Wang, Yifan and
Lan, Tian and
Gan, Yanglei and
Lin, Run and
Liu, Leyuan and
Wu, Zufeng and
Yan, Xiaoyue and
Wu, Xiaohua",
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.1848/",
pages = "39471--39487",
ISBN = "979-8-89176-462-0",
abstract = "Template-based approaches have advanced Event Argument Extraction (EAE) by formulating it as a structured prediction problem. However, existing methods mainly rely on either fixed manually designed templates, which suffer from template under-matching in diverse contexts, or exhaustive enumeration of template permutations, incurring prohibitively high computational cost. Moreover, they often overlook the semantic heterogeneity across events. To address these challenges, we propose ATSR, an Adaptive Template Selection and Role-Aware Routing framework for document-level multi-event EAE, integrating an Adaptive Multi-structure Template Selection (AMSTS) module and a Role-Aware Mixture-of-Experts (RAMoE) module. Specifically, AMSTS leverages a set of pre-defined multi-structure templates for each event type and adaptively selects the most compatible one for each event based on learnable weights conditioned on trigger representations. The RAMoE operates over template-aligned slots and routes each role to specialized experts for event semantic modeling. Extensive experiments on three benchmark datasets demonstrate that ATSR achieves state-of-the-art performance with competitive efficiency, while remaining effective in few-shot settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-atsr">
<titleInfo>
<title>ATSR: Adaptive Template Selection and Role-Aware Routing for Document-Level Multi-Event Argument Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanglei</namePart>
<namePart type="family">Gan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Run</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zufeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyue</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohua</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>Template-based approaches have advanced Event Argument Extraction (EAE) by formulating it as a structured prediction problem. However, existing methods mainly rely on either fixed manually designed templates, which suffer from template under-matching in diverse contexts, or exhaustive enumeration of template permutations, incurring prohibitively high computational cost. Moreover, they often overlook the semantic heterogeneity across events. To address these challenges, we propose ATSR, an Adaptive Template Selection and Role-Aware Routing framework for document-level multi-event EAE, integrating an Adaptive Multi-structure Template Selection (AMSTS) module and a Role-Aware Mixture-of-Experts (RAMoE) module. Specifically, AMSTS leverages a set of pre-defined multi-structure templates for each event type and adaptively selects the most compatible one for each event based on learnable weights conditioned on trigger representations. The RAMoE operates over template-aligned slots and routes each role to specialized experts for event semantic modeling. Extensive experiments on three benchmark datasets demonstrate that ATSR achieves state-of-the-art performance with competitive efficiency, while remaining effective in few-shot settings.</abstract>
<identifier type="citekey">wang-etal-2026-atsr</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1848/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>39471</start>
<end>39487</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ATSR: Adaptive Template Selection and Role-Aware Routing for Document-Level Multi-Event Argument Extraction
%A Wang, Yifan
%A Lan, Tian
%A Gan, Yanglei
%A Lin, Run
%A Liu, Leyuan
%A Wu, Zufeng
%A Yan, Xiaoyue
%A Wu, Xiaohua
%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 wang-etal-2026-atsr
%X Template-based approaches have advanced Event Argument Extraction (EAE) by formulating it as a structured prediction problem. However, existing methods mainly rely on either fixed manually designed templates, which suffer from template under-matching in diverse contexts, or exhaustive enumeration of template permutations, incurring prohibitively high computational cost. Moreover, they often overlook the semantic heterogeneity across events. To address these challenges, we propose ATSR, an Adaptive Template Selection and Role-Aware Routing framework for document-level multi-event EAE, integrating an Adaptive Multi-structure Template Selection (AMSTS) module and a Role-Aware Mixture-of-Experts (RAMoE) module. Specifically, AMSTS leverages a set of pre-defined multi-structure templates for each event type and adaptively selects the most compatible one for each event based on learnable weights conditioned on trigger representations. The RAMoE operates over template-aligned slots and routes each role to specialized experts for event semantic modeling. Extensive experiments on three benchmark datasets demonstrate that ATSR achieves state-of-the-art performance with competitive efficiency, while remaining effective in few-shot settings.
%U https://aclanthology.org/2026.findings-emnlp.1848/
%P 39471-39487
Markdown (Informal)
[ATSR: Adaptive Template Selection and Role-Aware Routing for Document-Level Multi-Event Argument Extraction](https://aclanthology.org/2026.findings-emnlp.1848/) (Wang et al., Findings 2026)
ACL
- Yifan Wang, Tian Lan, Yanglei Gan, Run Lin, Leyuan Liu, Zufeng Wu, Xiaoyue Yan, and Xiaohua Wu. 2026. ATSR: Adaptive Template Selection and Role-Aware Routing for Document-Level Multi-Event Argument Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 39471–39487, Budapest, Hungary. Association for Computational Linguistics.