@inproceedings{zhang-etal-2026-multi-expert,
title = "Multi-Expert Routing for Event Graph Completion",
author = "Zhang, Qing and
Cai, Wei and
Liang, Chao and
Wang, Bang",
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.108/",
pages = "2229--2246",
ISBN = "979-8-89176-462-0",
abstract = "The task of event graph completion (EGC) aims to predict the missing relations between two events in a heterogeneous event graph (EG) to enhance its applicability in downstream tasks. Given that event graphs inherently contain both semantic and structural information, and that the effective aggregation of these two types of information can mutually reinforce their expressive power, we propose a **M**ulti-**E**xpert **R**outing (MER) framework, which leverages the mixture of experts (MoE) architecture to dynamically select appropriate experts for collaboratively addressing different key aspects of the EGC task. Specifically, our approach incorporates multiple specialized experts, leveraging prompt learning and a graph attention network, to independently model distinct semantic and structural features within EGs. Furthermore, an adaptive expert routing (AER) module is designed to dynamically fuse and select the missing relation predictions from the experts, thereby completing the EGs. Extensive experiments conducted on the EGC-MAVEN dataset demonstrate that our MER framework outperforms the state-of-the-art competitors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-multi-expert">
<titleInfo>
<title>Multi-Expert Routing for Event Graph Completion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bang</namePart>
<namePart type="family">Wang</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>The task of event graph completion (EGC) aims to predict the missing relations between two events in a heterogeneous event graph (EG) to enhance its applicability in downstream tasks. Given that event graphs inherently contain both semantic and structural information, and that the effective aggregation of these two types of information can mutually reinforce their expressive power, we propose a **M**ulti-**E**xpert **R**outing (MER) framework, which leverages the mixture of experts (MoE) architecture to dynamically select appropriate experts for collaboratively addressing different key aspects of the EGC task. Specifically, our approach incorporates multiple specialized experts, leveraging prompt learning and a graph attention network, to independently model distinct semantic and structural features within EGs. Furthermore, an adaptive expert routing (AER) module is designed to dynamically fuse and select the missing relation predictions from the experts, thereby completing the EGs. Extensive experiments conducted on the EGC-MAVEN dataset demonstrate that our MER framework outperforms the state-of-the-art competitors.</abstract>
<identifier type="citekey">zhang-etal-2026-multi-expert</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.108/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2229</start>
<end>2246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Expert Routing for Event Graph Completion
%A Zhang, Qing
%A Cai, Wei
%A Liang, Chao
%A Wang, Bang
%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 zhang-etal-2026-multi-expert
%X The task of event graph completion (EGC) aims to predict the missing relations between two events in a heterogeneous event graph (EG) to enhance its applicability in downstream tasks. Given that event graphs inherently contain both semantic and structural information, and that the effective aggregation of these two types of information can mutually reinforce their expressive power, we propose a **M**ulti-**E**xpert **R**outing (MER) framework, which leverages the mixture of experts (MoE) architecture to dynamically select appropriate experts for collaboratively addressing different key aspects of the EGC task. Specifically, our approach incorporates multiple specialized experts, leveraging prompt learning and a graph attention network, to independently model distinct semantic and structural features within EGs. Furthermore, an adaptive expert routing (AER) module is designed to dynamically fuse and select the missing relation predictions from the experts, thereby completing the EGs. Extensive experiments conducted on the EGC-MAVEN dataset demonstrate that our MER framework outperforms the state-of-the-art competitors.
%U https://aclanthology.org/2026.findings-emnlp.108/
%P 2229-2246
Markdown (Informal)
[Multi-Expert Routing for Event Graph Completion](https://aclanthology.org/2026.findings-emnlp.108/) (Zhang et al., Findings 2026)
ACL
- Qing Zhang, Wei Cai, Chao Liang, and Bang Wang. 2026. Multi-Expert Routing for Event Graph Completion. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 2229–2246, Budapest, Hungary. Association for Computational Linguistics.