Resumo -En la presente investigación se busca realizar un traductor de lenguaje natural español a SQL utilizando tanto el esquema de la base de datos como información del dominio, la cual se ingresará por medio de un archivo CSV. Para ello el sistema utilizará las preposiciones, artículos y principales adverbios del lenguaje español como parte de su análisis y se utilizará un algoritmo de aproximación, que de acuerdo a las palabras que se entiendan de la entrada del usuario, buscará generar una sentencia SQL. Por lo tanto, el problema que la presente investigación pretende resolver es la dificultad que tienen los usuarios no técnicos para acceder a las bases de datos, implementando para ello una interfaz en lenguaje natural.Abstract -In the present investigation we pretend to make a Spanish natural language translator to SQL using both the database schema and domain information, which is entered through a CSV file. For that end, the system uses prepositions, articles and main adverbs of Spanish language as part of their analysis and an approximation algorithm is used, it means, according to the words that are understood for the user input, the system will try to generate an SQL statement. Therefore, the problem wanted to be solved with this research is the difficulty that non-technical users have when doing queries to a database, implementing, for that reason, an interface in natural language.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.