Abstract
Abstract
The number of databases, as well as their size and complexity, is steadily increasing. This trend creates a significant barrier to data access, especially for non-expert users who must understand not only the content and structure of the data, but also the specific query languages or interfaces used to retrieve it. These challenges are even more pronounced in research environments, where users often need to interact with multiple, heterogeneous databases. One promising solution to this problem is enabling users to express their queries in natural language.
Natural Language Querying (NLQ) is a long-standing challenge in the field of information retrieval. It allows users to formulate queries without needing prior knowledge of formal query languages such as SQL. A natural language query typically consists of everyday words and phrases, ranging from complete grammatical sentences to sentence fragments, expressed without any special syntax. Processing such queries may involve simple keyword detection or more advanced techniques like syntactic parsing and semantic analysis.
In this context, developing effective natural language interfaces for databases is essential to bridge the gap between user intent and data retrieval, and remains an active area of research aiming to make data access more intuitive, inclusive, and efficient.