@inproceedings{pasquini-etal-2026-linguistic,
title = "Linguistic Initialization for Inductive Reasoning in Heterogeneous Knowledge Graphs",
author = "Pasquini, Daniele and
Croce, Danilo and
Basili, Roberto",
editor = "S{\'e}rasset, Gilles and
Gkirtzou, Katerina and
Cochez, Michael and
Kalo, Jan-Christoph",
booktitle = "Proceedings of the Knowledge Graphs and Large Language Models Workshop ({KG}-{LLM}) @ {LREC}26",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.kallm-1.1/",
doi = "10.63317/2cxo43n6o593",
pages = "1--10",
abstract = "Knowledge Graphs (KGs) provide explicit relational structure, while Large Language Models (LLMs) encode rich semantic knowledge. We propose a lightweight linguistic initialization strategy for heterogeneous link prediction that improves robustness under sparsity and imbalance. For each node, we construct a compact textual view combining intrinsic description and local neighborhood context, encode it with a pre-trained language model, and use the resulting embeddings to initialize a relation-aware GNN. This design preserves standard message passing while providing early semantically meaningful representations. Across multiple imbalance regimes and strict entity-to-entity cold-start settings, the proposed initialization consistently improves over random initialization and reduces degree-dependent degradation. Our results show that semantic grounding can be integrated into heterogeneous GNN pipelines with minimal architectural changes and strong empirical benefits."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pasquini-etal-2026-linguistic">
<titleInfo>
<title>Linguistic Initialization for Inductive Reasoning in Heterogeneous Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniele</namePart>
<namePart type="family">Pasquini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Croce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Basili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Sérasset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cochez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan-Christoph</namePart>
<namePart type="family">Kalo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge Graphs (KGs) provide explicit relational structure, while Large Language Models (LLMs) encode rich semantic knowledge. We propose a lightweight linguistic initialization strategy for heterogeneous link prediction that improves robustness under sparsity and imbalance. For each node, we construct a compact textual view combining intrinsic description and local neighborhood context, encode it with a pre-trained language model, and use the resulting embeddings to initialize a relation-aware GNN. This design preserves standard message passing while providing early semantically meaningful representations. Across multiple imbalance regimes and strict entity-to-entity cold-start settings, the proposed initialization consistently improves over random initialization and reduces degree-dependent degradation. Our results show that semantic grounding can be integrated into heterogeneous GNN pipelines with minimal architectural changes and strong empirical benefits.</abstract>
<identifier type="citekey">pasquini-etal-2026-linguistic</identifier>
<identifier type="doi">10.63317/2cxo43n6o593</identifier>
<location>
<url>https://aclanthology.org/2026.kallm-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Initialization for Inductive Reasoning in Heterogeneous Knowledge Graphs
%A Pasquini, Daniele
%A Croce, Danilo
%A Basili, Roberto
%Y Sérasset, Gilles
%Y Gkirtzou, Katerina
%Y Cochez, Michael
%Y Kalo, Jan-Christoph
%S Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F pasquini-etal-2026-linguistic
%X Knowledge Graphs (KGs) provide explicit relational structure, while Large Language Models (LLMs) encode rich semantic knowledge. We propose a lightweight linguistic initialization strategy for heterogeneous link prediction that improves robustness under sparsity and imbalance. For each node, we construct a compact textual view combining intrinsic description and local neighborhood context, encode it with a pre-trained language model, and use the resulting embeddings to initialize a relation-aware GNN. This design preserves standard message passing while providing early semantically meaningful representations. Across multiple imbalance regimes and strict entity-to-entity cold-start settings, the proposed initialization consistently improves over random initialization and reduces degree-dependent degradation. Our results show that semantic grounding can be integrated into heterogeneous GNN pipelines with minimal architectural changes and strong empirical benefits.
%R 10.63317/2cxo43n6o593
%U https://aclanthology.org/2026.kallm-1.1/
%U https://doi.org/10.63317/2cxo43n6o593
%P 1-10
Markdown (Informal)
[Linguistic Initialization for Inductive Reasoning in Heterogeneous Knowledge Graphs](https://aclanthology.org/2026.kallm-1.1/) (Pasquini et al., KaLLM 2026)
ACL