The text-to-SQL task aims to convert natural language into Structured Query Language (SQL) without bias. Recently, text-to-SQL methods based on large language models (LLMs) have garnered significant attention. The core of mainstream text-to-SQL frameworks is schema linking, which aligns user queries with relevant tables and columns in the database. Previous methods focused on schema linking while neglecting to enhance LLMs' understanding of database schema. The complex coupling relationships between tables in the database constrain the SQL generation capabilities of LLMs. To tackle this issue, this paper proposes a simple yet effective strategy called view-based schema. This strategy aids LLMs in understanding the database schema by decoupling tightly coupled tables into low-coupling views. We then introduce V-SQL, a view-based two-stage text-to-SQL framework. V-SQL involves the view-based schema strategy to enhance LLMs' understanding of database schema. Results on the authoritative datasets Bird indicate that V-SQL achieves competitive performance compared to existing state-of-the-art methods.

Correspondingly, a customer for artificial intelligence will begin functioning in the Defense Ministry from next year," Osyko said at a conference on …

Mixed Integer Programming (MIP) is one of the most widely used modeling techniques to deal with combinatorial optimization problems. In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients. This offers the opportunity for machine learning method to explore the correlations between model structures and the resulting solution values. To address this issue, we propose to represent an MIP instance using a tripartite graph, based on which a Graph Convolutional Network (GCN) is constructed to predict solution values for binary variables. The predicted solutions are used to generate a local branching cut to the model which accelerate the solution process for MIP. Computational evaluations on 8 distinct types of MIP problems show that the proposed framework improves the performance of a state-of-the-art open source MIP solver significantly in terms of running time and solution quality.

Igor Kononenko studied computer science at the University of Ljubliana, Slovenia, receiving his BSc in 1982, MSc in 1985 and PhD in 1990. He is now professor at the Faculty of Computer and Information Science there, teaching courses in Programming Languages, Algorithms and Data Structures; Introduction to Algorithms and Data Structures; Knowledge Engineering, Machine Learning and Knowledge Discovery in Databases. He is the head of the Laboratory for Cognitive Modelling and a member of the Artificial Intelligence Department at the same faculty. His research interests include artificial intelligence, machine learning, neural networks and cognitive modelling. He is the (co) author of 170 scientific papers in these fields and 10 textbooks.