@inproceedings{cazzaro-etal-2025-spot,
title = "{SPOT}: Zero-Shot Semantic Parsing Over Property Graphs",
author = "Cazzaro, Francesco and
Kleindienst, Justin and
Gomez, Sofia M{\'a}rquez and
Quattoni, Ariadna",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.524/",
doi = "10.18653/v1/2025.findings-acl.524",
pages = "10057--10073",
ISBN = "979-8-89176-256-5",
abstract = "Knowledge Graphs (KGs) have gained popularity as a means of storing structured data, with property graphs, in particular, gaining traction in recent years. Consequently, the task of semantic parsing remains crucial in enabling access to the information in these graphs via natural language queries. However, annotated data is scarce, requires significant effort to create, and is not easily transferable between different graphs. To address these challenges we introduce SPOT, a method to generate training data for semantic parsing over Property Graphs without human annotations. We generate tree patterns, match them to the KG to obtain a query program, and use a finite-state transducer to produce a proto-natural language realization of the query. Finally, we paraphrase the proto-NL with an LLM to generate samples for training a semantic parser. We demonstrate the effectiveness of SPOT on two property graph benchmarks utilizing the Cypher query language. In addition, we show that our approach can also be applied effectively to RDF graphs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cazzaro-etal-2025-spot">
<titleInfo>
<title>SPOT: Zero-Shot Semantic Parsing Over Property Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Cazzaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Kleindienst</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofia</namePart>
<namePart type="given">Márquez</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariadna</namePart>
<namePart type="family">Quattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Knowledge Graphs (KGs) have gained popularity as a means of storing structured data, with property graphs, in particular, gaining traction in recent years. Consequently, the task of semantic parsing remains crucial in enabling access to the information in these graphs via natural language queries. However, annotated data is scarce, requires significant effort to create, and is not easily transferable between different graphs. To address these challenges we introduce SPOT, a method to generate training data for semantic parsing over Property Graphs without human annotations. We generate tree patterns, match them to the KG to obtain a query program, and use a finite-state transducer to produce a proto-natural language realization of the query. Finally, we paraphrase the proto-NL with an LLM to generate samples for training a semantic parser. We demonstrate the effectiveness of SPOT on two property graph benchmarks utilizing the Cypher query language. In addition, we show that our approach can also be applied effectively to RDF graphs.</abstract>
<identifier type="citekey">cazzaro-etal-2025-spot</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.524</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.524/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>10057</start>
<end>10073</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPOT: Zero-Shot Semantic Parsing Over Property Graphs
%A Cazzaro, Francesco
%A Kleindienst, Justin
%A Gomez, Sofia Márquez
%A Quattoni, Ariadna
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F cazzaro-etal-2025-spot
%X Knowledge Graphs (KGs) have gained popularity as a means of storing structured data, with property graphs, in particular, gaining traction in recent years. Consequently, the task of semantic parsing remains crucial in enabling access to the information in these graphs via natural language queries. However, annotated data is scarce, requires significant effort to create, and is not easily transferable between different graphs. To address these challenges we introduce SPOT, a method to generate training data for semantic parsing over Property Graphs without human annotations. We generate tree patterns, match them to the KG to obtain a query program, and use a finite-state transducer to produce a proto-natural language realization of the query. Finally, we paraphrase the proto-NL with an LLM to generate samples for training a semantic parser. We demonstrate the effectiveness of SPOT on two property graph benchmarks utilizing the Cypher query language. In addition, we show that our approach can also be applied effectively to RDF graphs.
%R 10.18653/v1/2025.findings-acl.524
%U https://aclanthology.org/2025.findings-acl.524/
%U https://doi.org/10.18653/v1/2025.findings-acl.524
%P 10057-10073
Markdown (Informal)
[SPOT: Zero-Shot Semantic Parsing Over Property Graphs](https://aclanthology.org/2025.findings-acl.524/) (Cazzaro et al., Findings 2025)
ACL
- Francesco Cazzaro, Justin Kleindienst, Sofia Márquez Gomez, and Ariadna Quattoni. 2025. SPOT: Zero-Shot Semantic Parsing Over Property Graphs. In Findings of the Association for Computational Linguistics: ACL 2025, pages 10057–10073, Vienna, Austria. Association for Computational Linguistics.