Use this link to cite:
http://hdl.handle.net/2183/39591 Web application for generating Entity-Relationship diagrams with Natural Language Processing
Loading...
Identifiers
Publication date
Authors
Sineiro Barreiro, David
Advisors
Other responsabilities
Universidade da Coruña. Facultade de Informática
Journal Title
Bibliographic citation
Type of academic work
Academic degree
Abstract
[Resumen]: Los ingenieros de software suelen utilizar diagramas Entidad-Relación (ER) para describir bases de datos relacionales porque ofrecen una forma clara y sencilla de representar los datos. Pero dibujar diagramas ER suele requerir conocimientos previos en modelado de datos. Este proyecto presenta un prototipo que utiliza grandes modelos de lenguaje (LLM), una forma de enfoque de procesamiento del lenguaje natural (PLN), para agilizar el proceso. El sistema produce salidas estructuradas en formatos comunes que pueden utilizarse para crear diagramas ER con sólo unas sencillas indicaciones al usuario. Para acercar este prototipo al usuario, desarrollamos una aplicación web con una interfaz fácil de usar que agiliza y hace más accesible el proceso de creación de diagramas.
[Abstract]: Software engineers frequently use Entity-Relationship (ER) diagrams to describe relational databases because they offer a clear and easy way of representing the data. But drawing ER diagrams usually requires previous knowledge in data modelling. This project presents a prototype that uses large language models (LLMs), a form of natural language processing (NLP) approach, to streamline the process. The system produces structured outputs in common formats that may be used to create ER diagrams with only a few simple user prompts. In order to bring this prototype to the user, we developed a web application with an easy-to-use interface that makes the process of creating diagrams faster and more accessible.
[Abstract]: Software engineers frequently use Entity-Relationship (ER) diagrams to describe relational databases because they offer a clear and easy way of representing the data. But drawing ER diagrams usually requires previous knowledge in data modelling. This project presents a prototype that uses large language models (LLMs), a form of natural language processing (NLP) approach, to streamline the process. The system produces structured outputs in common formats that may be used to create ER diagrams with only a few simple user prompts. In order to bring this prototype to the user, we developed a web application with an easy-to-use interface that makes the process of creating diagrams faster and more accessible.
Description
Editor version
Rights
Atribución 3.0 España








