@inproceedings{diallo-zouaq-2026-frase,
title = "{FRASE}: Frame-based Structured Representations for Generalizable {SPARQL} Query Generation",
author = "Diallo, Papa Abdou Karim Karou and
Zouaq, Amal",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.101/",
doi = "10.63317/52g4z7jtim8o",
pages = "1303--1319",
abstract = "Translating natural language questions into SPARQL queries enables Knowledge Base querying for factual and up-to-date responses. However, existing datasets for this task are predominantly template-based, leading models to learn superficial mappings between question and query templates rather than developing true generalization capabilities. As a result, models struggle when encountering naturally phrased, template-free questions. This paper introduces FRASE (FRAme-based Semantic Enhancement), a novel approach that leverages Frame Semantic Role Labeling (FSRL) to overcome this limitation. In addition, we present LCQ1-Frame, LCQ2-Frame, and QALD-10-Frame{---}a suite of new datasets derived from LC-QuAD 1.0, LC-QuAD 2.0, and QALD-10 where each question is enriched using FRASE through frame detection and the mapping of frame-elements to their corresponding arguments. We evaluate our approach for the Question-2-SPARQL task through extensive experiments using recent large language models (LLMs) under different fine-tuning configurations. Our results demonstrate that integrating frame-based structured representations consistently improves SPARQL generation performance, particularly in challenging generalization scenarios when test questions feature unseen templates (unknown template splits) and when they are all naturally phrased (reformulated questions)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diallo-zouaq-2026-frase">
<titleInfo>
<title>FRASE: Frame-based Structured Representations for Generalizable SPARQL Query Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Papa</namePart>
<namePart type="given">Abdou</namePart>
<namePart type="given">Karim</namePart>
<namePart type="given">Karou</namePart>
<namePart type="family">Diallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Zouaq</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translating natural language questions into SPARQL queries enables Knowledge Base querying for factual and up-to-date responses. However, existing datasets for this task are predominantly template-based, leading models to learn superficial mappings between question and query templates rather than developing true generalization capabilities. As a result, models struggle when encountering naturally phrased, template-free questions. This paper introduces FRASE (FRAme-based Semantic Enhancement), a novel approach that leverages Frame Semantic Role Labeling (FSRL) to overcome this limitation. In addition, we present LCQ1-Frame, LCQ2-Frame, and QALD-10-Frame—a suite of new datasets derived from LC-QuAD 1.0, LC-QuAD 2.0, and QALD-10 where each question is enriched using FRASE through frame detection and the mapping of frame-elements to their corresponding arguments. We evaluate our approach for the Question-2-SPARQL task through extensive experiments using recent large language models (LLMs) under different fine-tuning configurations. Our results demonstrate that integrating frame-based structured representations consistently improves SPARQL generation performance, particularly in challenging generalization scenarios when test questions feature unseen templates (unknown template splits) and when they are all naturally phrased (reformulated questions).</abstract>
<identifier type="citekey">diallo-zouaq-2026-frase</identifier>
<identifier type="doi">10.63317/52g4z7jtim8o</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.101/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1303</start>
<end>1319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FRASE: Frame-based Structured Representations for Generalizable SPARQL Query Generation
%A Diallo, Papa Abdou Karim Karou
%A Zouaq, Amal
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F diallo-zouaq-2026-frase
%X Translating natural language questions into SPARQL queries enables Knowledge Base querying for factual and up-to-date responses. However, existing datasets for this task are predominantly template-based, leading models to learn superficial mappings between question and query templates rather than developing true generalization capabilities. As a result, models struggle when encountering naturally phrased, template-free questions. This paper introduces FRASE (FRAme-based Semantic Enhancement), a novel approach that leverages Frame Semantic Role Labeling (FSRL) to overcome this limitation. In addition, we present LCQ1-Frame, LCQ2-Frame, and QALD-10-Frame—a suite of new datasets derived from LC-QuAD 1.0, LC-QuAD 2.0, and QALD-10 where each question is enriched using FRASE through frame detection and the mapping of frame-elements to their corresponding arguments. We evaluate our approach for the Question-2-SPARQL task through extensive experiments using recent large language models (LLMs) under different fine-tuning configurations. Our results demonstrate that integrating frame-based structured representations consistently improves SPARQL generation performance, particularly in challenging generalization scenarios when test questions feature unseen templates (unknown template splits) and when they are all naturally phrased (reformulated questions).
%R 10.63317/52g4z7jtim8o
%U https://aclanthology.org/2026.lrec-1.101/
%U https://doi.org/10.63317/52g4z7jtim8o
%P 1303-1319
Markdown (Informal)
[FRASE: Frame-based Structured Representations for Generalizable SPARQL Query Generation](https://aclanthology.org/2026.lrec-1.101/) (Diallo & Zouaq, LREC 2026)
ACL