@inproceedings{yu-etal-2026-bridging,
title = "Bridging Text and Structure via Latent Query Refinement for Knowledge Graph Completion",
author = "Yu, Chunmiao and
Wang, Zikang and
Luo, Tianyi and
Wang, Jiaojiao and
Cao, Zhidong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1315/",
pages = "29932--29945",
ISBN = "979-8-89176-459-0",
abstract = "Knowledge graph completion(KGC) aims to infer missing facts from observed relational triples, which demands jointly modeling textual semantics and relational structure. Existing structure-based methods capture graph topology but often struggle with sparse entities and long-tail relations, while text-based methods exploit entity and relation descriptions but weakly model relational neighborhoods. In this paper, we propose LQ-KGC, a latent-query refinement framework that enables iterative interaction between semantic inference and structural reasoning for KGC. Instead of treating all missing triples as latent variables, LQ-KGC constructs a restricted set of semantically plausible latent queries and alternates between two refinement steps: the language model predicts latent tail distributions from textual descriptions, while the graph model incorporates high-confidence pseudo tails as pseudo edges for relation-aware message passing. Meanwhile, structure-aware graph predictions are distilled back into the language model to refine semantic representations. Experiments on WN18RR and FB15k-237 demonstrate that LQ-KGC consistently improves over text-based and graph-based baselines, with additional analyses highlighting the effectiveness of pseudo-edge augmentation and latent-query construction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2026-bridging">
<titleInfo>
<title>Bridging Text and Structure via Latent Query Refinement for Knowledge Graph Completion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chunmiao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zikang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaojiao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhidong</namePart>
<namePart type="family">Cao</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Knowledge graph completion(KGC) aims to infer missing facts from observed relational triples, which demands jointly modeling textual semantics and relational structure. Existing structure-based methods capture graph topology but often struggle with sparse entities and long-tail relations, while text-based methods exploit entity and relation descriptions but weakly model relational neighborhoods. In this paper, we propose LQ-KGC, a latent-query refinement framework that enables iterative interaction between semantic inference and structural reasoning for KGC. Instead of treating all missing triples as latent variables, LQ-KGC constructs a restricted set of semantically plausible latent queries and alternates between two refinement steps: the language model predicts latent tail distributions from textual descriptions, while the graph model incorporates high-confidence pseudo tails as pseudo edges for relation-aware message passing. Meanwhile, structure-aware graph predictions are distilled back into the language model to refine semantic representations. Experiments on WN18RR and FB15k-237 demonstrate that LQ-KGC consistently improves over text-based and graph-based baselines, with additional analyses highlighting the effectiveness of pseudo-edge augmentation and latent-query construction.</abstract>
<identifier type="citekey">yu-etal-2026-bridging</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1315/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>29932</start>
<end>29945</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging Text and Structure via Latent Query Refinement for Knowledge Graph Completion
%A Yu, Chunmiao
%A Wang, Zikang
%A Luo, Tianyi
%A Wang, Jiaojiao
%A Cao, Zhidong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yu-etal-2026-bridging
%X Knowledge graph completion(KGC) aims to infer missing facts from observed relational triples, which demands jointly modeling textual semantics and relational structure. Existing structure-based methods capture graph topology but often struggle with sparse entities and long-tail relations, while text-based methods exploit entity and relation descriptions but weakly model relational neighborhoods. In this paper, we propose LQ-KGC, a latent-query refinement framework that enables iterative interaction between semantic inference and structural reasoning for KGC. Instead of treating all missing triples as latent variables, LQ-KGC constructs a restricted set of semantically plausible latent queries and alternates between two refinement steps: the language model predicts latent tail distributions from textual descriptions, while the graph model incorporates high-confidence pseudo tails as pseudo edges for relation-aware message passing. Meanwhile, structure-aware graph predictions are distilled back into the language model to refine semantic representations. Experiments on WN18RR and FB15k-237 demonstrate that LQ-KGC consistently improves over text-based and graph-based baselines, with additional analyses highlighting the effectiveness of pseudo-edge augmentation and latent-query construction.
%U https://aclanthology.org/2026.emnlp-main.1315/
%P 29932-29945
Markdown (Informal)
[Bridging Text and Structure via Latent Query Refinement for Knowledge Graph Completion](https://aclanthology.org/2026.emnlp-main.1315/) (Yu et al., EMNLP 2026)
ACL