Related papers: Learning SQL from within: integrating database exe…

Flexible business processes can often be modelled more easily using a declarative rather than a procedural modelling approach. Process mining aims at automating the discovery of business process models. Existing declarative process mining…

MADlib is a free, open source library of in-database analytic methods. It provides an evolving suite of SQL-based algorithms for machine learning, data mining and statistics that run at scale within a database engine, with no need for data…

The task of context-dependent text-to-SQL aims to convert multi-turn user utterances to formal SQL queries. This is a challenging task due to both the scarcity of training data from which to learn complex contextual dependencies and to…

Recent progress in language model pre-training has achieved a great success via leveraging large-scale unstructured textual data. However, it is still a challenge to apply pre-training on structured tabular data due to the absence of…

Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a "prompt-and-pray" paradigm, where the user has limited control and insight into the intermediate reasoning steps used to achieve the final…

Recently, we have proposed a model-driven approach for enforcing fine-grained access control (FGAC) policies when executing SQL queries. More concretely, we have defined a function SecQuery() that, given an FGAC policy S and a SQL…

This paper presents a new technique for automatically synthesizing SQL queries from natural language. Our technique is fully automated, works for any database without requiring additional customization, and does not require users to know…

Semantic parsing is the task of mapping natural language to logic form. In question answering, semantic parsing can be used to map the question to logic form and execute the logic form to get the answer. One key problem for semantic parsing…

Its constant technological evolution characterizes the contemporary world, and every day the processes, once manual, become computerized. Data are stored in the cyberspace, and as a consequence, one must increase the concern with the…

AI-Powered database (AI-DB) is a novel relational database system that uses a self-supervised neural network, database embedding, to enable semantic SQL queries on relational tables. In this paper, we describe an architecture and…

Detecting structural similarity between queries is essential for selecting examples in in-context learning models. However, assessing structural similarity based solely on the natural language expressions of queries, without considering SQL…

We discuss the advantages of searchable, collaborative, language-independent databases of mathematical results, indexed by "fingerprints" of small and canonical data. Our motivating example is Neil Sloane's massively influential On-Line…

Text-to-SQL parsing is an essential and challenging task. The goal of text-to-SQL parsing is to convert a natural language (NL) question to its corresponding structured query language (SQL) based on the evidences provided by relational…

Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most existing frameworks rely on dynamic commercial search APIs,…

SQL Injection (SQLi) continues to pose a significant threat to the security of web applications, enabling attackers to manipulate databases and access sensitive information without authorisation. Although advancements have been made in…

Asymmetric self-play has emerged as a promising paradigm for post-training large language models, where a teacher continually generates questions for a student to solve at the edge of the student's learnability. Although these methods…

In recent years, the task of text-to-SQL translation, which converts natural language questions into executable SQL queries, has gained significant attention for its potential to democratize data access. Despite its promise, challenges such…

In this demonstration, we present AnDB, an AI-native database that supports traditional OLTP workloads and innovative AI-driven tasks, enabling unified semantic analysis across structured and unstructured data. While structured data…

We consider machine learning models, learned from data, to be an important, intensional, kind of data in themselves. As such, various analysis tasks on models can be thought of as queries over this intensional data, often combined with…

Data mining and information extraction from data is a field that has gained relevance in recent years thanks to techniques based on artificial intelligence and use of machine and deep learning. The main aim of the present work is the…