Marta Breunig Loose · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · 2013
Even with the extensive use of XML as the standard for data exchange, most corporate data is stored in Relational Databases (RDB). Furthermore, many applications require efficient storage of XML data (eXtensible Markup Language), which can be achieved using a RDB. Thus, the ability to manage both kinds of data (relational and XML) becomes essential for organizations. Therefore, one of the alternatives to perform this storage consists of mapping the structure of XML documents to a relational schema. This mapping becomes complex since the XML documents have different structures even representing data from a common domain. In this case, in addition to mapping the structure and the XML data to relations in a RBD, it is also required to translate XML queries to SQL, the standard language used by RBD. In order to perform this translation, this work proposes a mechanism that translates XQuery queries to equivalent SQL queries, called QMap (Query Mapper). The proposal is part of a framework named X2Rel (XML to Relational), an environment for storing, managing and querying XML data in heterogeneous RBDs.
Cited by 0
Jixue Liu, Millist W. Vincent · 2003
XML has been accepted as a universal format for data interchange and publication. It can be applied in the applications in which the data of a database needs to be viewed in XML format so that the data being viewed takes more semantics and is easily understood. In these applications, the user of the data to be viewed sees only XML data, not the database. He may use XML query languages such as XSLT to query data and the retrieved data is presented in XML format to them. We are interested in the connection between the data that the user sees and the data in the database. More specifically, we are interested in translating XSLT queries to SQL queries.
Cited by 7
Michael Frame, Mehdi Owrang · Information Sciences · 1993
Cited by 1
Salem, Omar · TU/e Research Portal
Cited by 0
Ankit Agrahari, Puneet Kumar Ojha, Abhishek Gautam et al. · Preprints.org · 2024
Large Language Models (LLMs) have proved significant proficiency when comes to code generation especially in Structured Query Language (SQL) for databases and recent successful Text-to-SQL method involves fine-tuning pre-trained LLMs for SQL generation tasks. Transforming natural language text into SQL queries, has been attempted to solve with various learning techniques including Few-shot learning[1], fine tuning. In this paper we propose Supervised fine-tuning (SFT) as a better alternative for learning technique for text-to-SQL generation task using Code-Llama that pushes state of art accuracy on spider test suite to 89.6% on dev set which represent first instance of surpassing the earlier best-in-class with 5.5% higher score and 86.8% of exact match accuracy on dev set. Furthermore, we demonstrate that properly prompted LLM along with SFT provides far fewer hallucinations and much more robust LLM that can be used as a general tool for any text-to-SQL generation use case.
Cited by 2Open access
Ftoon Kedwan · Journal of King Saud University - Computer and Information Sciences · 2022
This research discusses the implementation experiment of an automatic translation of an unstructured Natural Language Question (NLQ) into a Structured Query Language (SQL) statement. SQL is used as a Relational DataBase (RDB) interaction language with special query syntax and a computer- executable artificial language. This way, DataBase (DB) administrators or general users with little or no SQL querying abilities can perform queries on RDBs in an interactive manner. The main goal of this work is to exploit a manually written rule- based mapping constraints algorithm. This algorithm maps NLQ tokens’ semantic/syntactic information into RDB elements’ semantic roles (i.e., value, attribute) via pairing and matching means. The matching RDB elements, called “identified lexica”, are then mapped into the SQL clauses consistently for SQL generation and execution. The matching process uses a computational linguistic analysis mapping algorithm, represented in the MetaTables. This mapping algorithm proved to be efficient especially with small RDBs with an accuracy of 95% and is about 93% accurate with larger RDBS.
Cited by 1Open access
Wenhua Yu, Zhenhao Chen, Haibo Liu et al. · 2024
With the advancement of domestic substitution strategies, migrating existing office software systems to domestically produced server platforms has become an urgent mission. This paper centers on the localization translation of SQL dialects within office information systems, specifically focusing on the translation from SQL Server to ShenTong Database. This paper presents a detailed SQL translation strategy and technical solution, and develops a SQL dialect intelligent translation tool, which is capable of automatically identifying and handling discrepancies between SQL statements from the two databases. This tool improves efficiency and accuracy of translation significantly. The effectiveness and feasibility of the proposed methodologies have been verified through empirical analysis, it has contributed important technical support and practical guidance to the localization of office information systems. The research also provides new perspectives and ideas for theoretical research and technical development in related fields, and provides practical and feasible technical references for relevant enterprises and departments in the process of localization transformation, effectively promoted the domestic information construction process.
Cited by 0
K. Bhargavi, H. S. Chaithra · 2013
SQL (Structured Query Language) was one of the standarized query language for requesting information from a database. Over the past few years organizations are using SQL for storing and managing the organization specific information. At the same time there is an emerging trend towards XML (Extensible Markup Language), and it has become a standard for information exchange over the internet. Users/Developers are supposed to use two different kinds of languages for data reception and manipulation. This problem is overcomed by converting the user's SQL queries into XML. In this paper, we propose a framework to convert SQL join (Left, Right, and Full) queries into XPath expressions. As a result user's can access XML database through SQL queries only. We also present algorithms for translating SQL join queries to XPath expressions.
Cited by 3
Oscar Romero, Alberto Abelló · 2008
In the last years, despite a vast amount of work have been devoted to modeling multidimensionality, multidimensional algebra translation to SQL have been overlooked. ROLAP tools automatically generate a cubequery according to the operations performed by the user. The SQL translation does not represent a problem when treating isolated operations but when mixing up together modifications brought about by a set of operations in the same cube-query, some conflicts could emerge depending on the operations involved. Therefore, if these problems are not detected and treated appropriately, the automatic translation can retrieve unexpected results. In this paper, we define and classify conflicts raised when automatically translating a multidimensional algebra to SQL, and analyze how to solve or minimize their impact.
Cited by 0
Boberg, Davi, Gomes-Jr, Luiz Celso, Rosa, Marcelo de Oliveira et al. · Zenodo (CERN European Organization for Nuclear Research) · 2017
As cloud services are becoming an alternative for IT infrastructures in many organizations, data privacy guarantees<br> become a priority. This paper presents the development of a secure database system using Intel’s SGX trusted platform.<br> SGX provides hardware-based processing privacy offering protection for a wide range of sophisticated attacks.<br> We propose a modular, multi-service architecture that is well suited to the advantages and limitations of the SGX platform.<br> This paper focuses on the ongoing implementation of our SQL translation service.
Cited by 0Open access
Boberg, Davi, Gomes-Jr, Luiz Celso, Rosa, Marcelo de Oliveira et al. · Zenodo (CERN European Organization for Nuclear Research) · 2017
As cloud services are becoming an alternative for IT infrastructures in many organizations, data privacy guarantees<br> become a priority. This paper presents the development of a secure database system using Intel’s SGX trusted platform.<br> SGX provides hardware-based processing privacy offering protection for a wide range of sophisticated attacks.<br> We propose a modular, multi-service architecture that is well suited to the advantages and limitations of the SGX platform.<br> This paper focuses on the ongoing implementation of our SQL translation service.
Cited by 0Open access
Martijn J. Schuemie, Marc A. Suchard · 2016
A rendering tool for parameterized SQL that also translates into different SQL dialects. These dialects include 'Microsoft SQL Server', 'Oracle', 'PostgreSql', 'Amazon RedShift', 'Apache Impala', 'IBM Netezza', 'Google BigQuery', 'Microsoft PDW', 'Snowflake', 'Azure Synapse Analytics Dedicated', 'Apache Spark', 'SQLite', and 'InterSystems IRIS'.
Cited by 0Open access
Minout, M., Parent, Christine, Zimanyi, Esteban · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2004
Cited by 0
Caferoğlu, Hasan Alp, Çelik, Mehmet Serhat, Ulusoy, Özgür · ArXiv.org · 2025
Translating natural language questions into SQL has become a core challenge in enabling non-technical users to query databases. While recent work has explored large-scale synthetic data generation to improve model performance through post-training, most efforts emphasize cross-domain generalization. This leaves a gap for real-world enterprise scenarios, where models need to specialize to a single database schema and organizations require to be able to evaluate their Text-to-SQL systems on their own databases. To address this, we introduce SING-SQL, a fully automated two-stage framework for generating high-quality, high-coverage synthetic Text-to-SQL data for any target database, without relying on SQL logs or manual annotations. Our approach hierarchically partitions a database schema into sub-schemas, synthesizes SQL queries across multiple complexity levels, and applies a quality-aware pipeline that includes LLM-as-a-judge validation, executability checks, automatic repair, and column balancing. We further release SingSQL-LM, a family of compact language models fine-tuned on the synthetic data, achieving strong in-domain generalization. On the subset of the BIRD benchmark, SingSQL-LM-3B-R64 reaches 82.87% Soft F1 and 73.03% EX upper bound with 32 candidates, outperforming the best 3B-scale baseline by +16.21 in Soft F1 and +12.36 in EX. At the 1.5B scale, SingSQL-LM-1.5B-R64 improves over prior systems by +9.30 in Soft F1 and +4.49 in EX. On synthetic evaluation sets, SingSQL-LMs exceed prior systems by wide margins, establishing state-of-the-art performance among open models at comparable scales. Our study of context management strategies reveals that schema-free fine-tuning combined with schema-only inference provides the most robust results. These findings establish SING-SQL as a scalable, database-agnostic paradigm for producing and evaluating enterprise-grade Text-to-SQL systems.
Cited by 0Open access
Z. Tang, Qian Ma, Di Wu · IET conference proceedings. · 2025
Using the best Text-to-SQL methods in resource-constrained environments is challenging due to their reliance on resource-intensive open-source models. This paper introduces Auto Prompt SQL (AP-SQL), a novel architecture designed to bridge the gap between resource-efficient small open-source models and the powerful capabilities of large closed-source models for Text-to-SQL translation. Our method decomposes the task into schema filtering, retrieval-augmented text-to-SQL generation based on in-context examples, and prompt-driven schema linking and SQL generation. To improve schema selection accuracy, we fine-tune large language models. Crucially, we also explore the impact of prompt engineering throughout the process, leveraging Chain-of-Thought (CoT) and Graph-of-Thought (GoT) templates to significantly enhance the model's reasoning for accurate SQL generation. Comprehensive evaluations on the Spider benchmarks demonstrate the effectiveness of AP-SQL.
Cited by 0
Z. Tang, Qian Ma, Di Wu · ArXiv.org · 2025
Using the best Text-to-SQL methods in resource-constrained environments is challenging due to their reliance on resource-intensive open-source models. This paper introduces Auto Prompt SQL(AP-SQL), a novel architecture designed to bridge the gap between resource-efficient small open-source models and the powerful capabilities of large closed-source models for Text-to-SQL translation. Our method decomposes the task into schema filtering, retrieval-augmented text-to-SQL generation based on in-context examples, and prompt-driven schema linking and SQL generation. To improve schema selection accuracy, we fine-tune large language models. Crucially, we also explore the impact of prompt engineering throughout the process, leveraging Chain-of-Thought(CoT) and Graph-of-Thought(GoT) templates to significantly enhance the model's reasoning for accurate SQL generation. Comprehensive evaluations on the Spider benchmarks demonstrate the effectiveness of AP-SQL.
Cited by 0Open access
Guo‐Qiang Zhang, Yuanchao Xu, Xipeng Shen et al. · Proceedings of the ACM on Programming Languages · 2021
Many data processing systems allow SQL queries that call user-defined functions (UDFs) written in conventional programming languages. While such SQL extensions provide convenience and flexibility to users, queries involving UDFs are not as efficient as their pure SQL counterparts that invoke SQL’s highly-optimized built-in functions. Motivated by this problem, we propose a new technique for translating SQL queries with UDFs to pure SQL expressions. Unlike prior work in this space, our method is not based on syntactic rewrite rules and can handle a much more general class of UDFs. At a high-level, our method is based on counterexample-guided inductive synthesis (CEGIS) but employs a novel compositional strategy that decomposes the synthesis task into simpler sub-problems. However, because there is no universal decomposition strategy that works for all UDFs, we propose a novel lazy inductive synthesis approach that generates a sequence of decompositions that correspond to increasingly harder inductive synthesis problems. Because most realistic UDF-to-SQL translation tasks are amenable to a fine-grained decomposition strategy, our lazy inductive synthesis method scales significantly better than traditional CEGIS. We have implemented our proposed technique in a tool called CLIS for optimizing Spark SQL programs containing Scala UDFs. To evaluate CLIS, we manually study 100 randomly selected UDFs and find that 63 of them can be expressed in pure SQL. Our evaluation on these 63 UDFs shows that CLIS can automatically synthesize equivalent SQL expressions in 92% of the cases and that it can solve 2.4× more benchmarks compared to a baseline that does not use our compositional approach. We also show that CLIS yields an average speed-up of 3.5× for individual UDFs and 1.3× to 3.1× in terms of end-to-end application performance.
Cited by 13Open access
SIAU, Keng, CHAN, H. · Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · 1991
Cited by 0Open access
Rareș Mihai Dinu, Marian Cristian Mihăescu, Traian Rebedea · 2023
This paper introduces a system specifically designed for natural language to SQL translation. Leveraging the power of machine learning, the system incorporates deep learning models, namely RAT-SQL and RoBERTa, to improve the accuracy and effectiveness of the translation process. The paper provides an in-depth overview of the system's highlevel design, including using RAT-SQL as the core model and integrating the BERT approach for enhanced performance. It also discusses the dataset employed during the system's development and presents the results and conclusions. By utilising the synergy of RAT-SQL and RoBERTa, the system demonstrates promising advancements in the natural language to SQL translation domain, showcasing its potential to simplify and streamline the interaction between human language and structured database queries.
Cited by 0Open access
Wensheng Tang · Computer Fraud & Security · 2024
Limitations of Oracle database in business support, development, operation, and maintenance hinder marketing 2.0's growth. Translating Oracle SQL statements to domestic databases is vital. A neural machine translation model based on migration learning resolves the lack of parallel corpus between Oracle and domestic databases. Encoder and decoder parameters of both databases' models are initialized using a trained Oracle database-side encoder and domestic database-side decoder. Fine-tuning and optimization produce high-quality parameters, improving translation performance. Results showed that the bilingual evaluation understudy (BLEU) of model reached 31.20 and an execution accuracy value of 84.3, outperforming the Transformer model by 13.28 and 13.3, respectively. Demonstrate support for database migration.
Cited by 0Open access