@inproceedings{quan-etal-2026-context,
title = "{C}on{TE}x{T}: Temporal Knowledge Graph Question Answering via Contractive Dual-Space Subgraph Search",
author = "Quan, Xu and
Yin, Yanting and
Li, Shiying and
Zhang, Wensheng",
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.706/",
pages = "14836--14847",
ISBN = "979-8-89176-462-0",
abstract = "Temporal Knowledge Graph Question Answering (TKGQA) commonly relies on retrieval-aggregation-reasoning pipelines, which suffer from two critical challenges: error propagation, where early retrieval mistakes accumulate along reasoning paths, and temporal conflicts caused by post-hoc temporal filtering, leaving temporally inconsistent paths in the search space and undermining multi-hop reasoning reliability. To address these limitations, we propose ConTExT (Contractive Temporal Exploration), a contractive subgraph search framework over structural and temporal spaces for TKGQA. It dynamically anchors question-relevant entities, performs selective subgraph exploration guided by path semantics and sub-question consistency, and applies Temporal Feasible Region Propagation (TFRP), which actively propagates temporal constraints during search and maintains a temporal feasible region. Experiments on MultiTQ show that ConTExT is particularly effective for complex temporal reasoning, yielding a 27.1{\%} relative improvement in Hits@1 over the strongest baseline on Multiple questions. Its gains are smaller on Single and Time-answer questions that depend more on direct evidence matching or exact temporal endpoints."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="quan-etal-2026-context">
<titleInfo>
<title>ConTExT: Temporal Knowledge Graph Question Answering via Contractive Dual-Space Subgraph Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Quan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanting</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiying</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wensheng</namePart>
<namePart type="family">Zhang</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>Temporal Knowledge Graph Question Answering (TKGQA) commonly relies on retrieval-aggregation-reasoning pipelines, which suffer from two critical challenges: error propagation, where early retrieval mistakes accumulate along reasoning paths, and temporal conflicts caused by post-hoc temporal filtering, leaving temporally inconsistent paths in the search space and undermining multi-hop reasoning reliability. To address these limitations, we propose ConTExT (Contractive Temporal Exploration), a contractive subgraph search framework over structural and temporal spaces for TKGQA. It dynamically anchors question-relevant entities, performs selective subgraph exploration guided by path semantics and sub-question consistency, and applies Temporal Feasible Region Propagation (TFRP), which actively propagates temporal constraints during search and maintains a temporal feasible region. Experiments on MultiTQ show that ConTExT is particularly effective for complex temporal reasoning, yielding a 27.1% relative improvement in Hits@1 over the strongest baseline on Multiple questions. Its gains are smaller on Single and Time-answer questions that depend more on direct evidence matching or exact temporal endpoints.</abstract>
<identifier type="citekey">quan-etal-2026-context</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.706/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>14836</start>
<end>14847</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConTExT: Temporal Knowledge Graph Question Answering via Contractive Dual-Space Subgraph Search
%A Quan, Xu
%A Yin, Yanting
%A Li, Shiying
%A Zhang, Wensheng
%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 quan-etal-2026-context
%X Temporal Knowledge Graph Question Answering (TKGQA) commonly relies on retrieval-aggregation-reasoning pipelines, which suffer from two critical challenges: error propagation, where early retrieval mistakes accumulate along reasoning paths, and temporal conflicts caused by post-hoc temporal filtering, leaving temporally inconsistent paths in the search space and undermining multi-hop reasoning reliability. To address these limitations, we propose ConTExT (Contractive Temporal Exploration), a contractive subgraph search framework over structural and temporal spaces for TKGQA. It dynamically anchors question-relevant entities, performs selective subgraph exploration guided by path semantics and sub-question consistency, and applies Temporal Feasible Region Propagation (TFRP), which actively propagates temporal constraints during search and maintains a temporal feasible region. Experiments on MultiTQ show that ConTExT is particularly effective for complex temporal reasoning, yielding a 27.1% relative improvement in Hits@1 over the strongest baseline on Multiple questions. Its gains are smaller on Single and Time-answer questions that depend more on direct evidence matching or exact temporal endpoints.
%U https://aclanthology.org/2026.findings-emnlp.706/
%P 14836-14847
Markdown (Informal)
[ConTExT: Temporal Knowledge Graph Question Answering via Contractive Dual-Space Subgraph Search](https://aclanthology.org/2026.findings-emnlp.706/) (Quan et al., Findings 2026)
ACL