@inproceedings{kreitlow-oliveira-2026-describe,
title = "To Describe or Not to Describe? Benchmarking Database Representations for Schema Linking in Text-to-{SQL}",
author = "Kreitlow, Daiane Ucceli and
Oliveira, Hil{\'a}rio Tomaz Alves de",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-1.15/",
pages = "151--160",
ISBN = "979-8-89176-387-6",
abstract = "Text-to-SQL systems aim to translate natural language questions into Structured Query Language (SQL) queries, enabling database access without requiring SQL expertise. In real-world scenarios, these systems often need to manage multiple databases with heterogeneous schemas, making Schema Linking a crucial preliminary step for identifying relevant databases, tables, and columns. This study investigates Schema Linking for questions written in Brazilian Portuguese and compares two schema representation strategies: natural-language descriptions generated by Large Language Models (LLMs) and representations based on Data Definition Language (DDL) and Data Manipulation Language (DML) commands. Experiments conducted on a Brazilian Portuguese version of the Spider dataset, with over 200 databases, evaluated several LLMs and embedding models. The experimental results based on Hit@k show that natural language descriptions consistently outperform DDL/DML-based representations, demonstrating the effectiveness of LLM-generated schema descriptions for Schema Linking tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kreitlow-oliveira-2026-describe">
<titleInfo>
<title>To Describe or Not to Describe? Benchmarking Database Representations for Schema Linking in Text-to-SQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daiane</namePart>
<namePart type="given">Ucceli</namePart>
<namePart type="family">Kreitlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hilário</namePart>
<namePart type="given">Tomaz</namePart>
<namePart type="given">Alves</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>Text-to-SQL systems aim to translate natural language questions into Structured Query Language (SQL) queries, enabling database access without requiring SQL expertise. In real-world scenarios, these systems often need to manage multiple databases with heterogeneous schemas, making Schema Linking a crucial preliminary step for identifying relevant databases, tables, and columns. This study investigates Schema Linking for questions written in Brazilian Portuguese and compares two schema representation strategies: natural-language descriptions generated by Large Language Models (LLMs) and representations based on Data Definition Language (DDL) and Data Manipulation Language (DML) commands. Experiments conducted on a Brazilian Portuguese version of the Spider dataset, with over 200 databases, evaluated several LLMs and embedding models. The experimental results based on Hit@k show that natural language descriptions consistently outperform DDL/DML-based representations, demonstrating the effectiveness of LLM-generated schema descriptions for Schema Linking tasks.</abstract>
<identifier type="citekey">kreitlow-oliveira-2026-describe</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.15/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>151</start>
<end>160</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Describe or Not to Describe? Benchmarking Database Representations for Schema Linking in Text-to-SQL
%A Kreitlow, Daiane Ucceli
%A Oliveira, Hilário Tomaz Alves de
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F kreitlow-oliveira-2026-describe
%X Text-to-SQL systems aim to translate natural language questions into Structured Query Language (SQL) queries, enabling database access without requiring SQL expertise. In real-world scenarios, these systems often need to manage multiple databases with heterogeneous schemas, making Schema Linking a crucial preliminary step for identifying relevant databases, tables, and columns. This study investigates Schema Linking for questions written in Brazilian Portuguese and compares two schema representation strategies: natural-language descriptions generated by Large Language Models (LLMs) and representations based on Data Definition Language (DDL) and Data Manipulation Language (DML) commands. Experiments conducted on a Brazilian Portuguese version of the Spider dataset, with over 200 databases, evaluated several LLMs and embedding models. The experimental results based on Hit@k show that natural language descriptions consistently outperform DDL/DML-based representations, demonstrating the effectiveness of LLM-generated schema descriptions for Schema Linking tasks.
%U https://aclanthology.org/2026.propor-1.15/
%P 151-160
Markdown (Informal)
[To Describe or Not to Describe? Benchmarking Database Representations for Schema Linking in Text-to-SQL](https://aclanthology.org/2026.propor-1.15/) (Kreitlow & Oliveira, PROPOR 2026)
ACL