Natural Language Interface to Database (NLIDB) for Interrogative Sentences with Temporal Elements in Indonesian Language

Natural Language Interface to Database (NLIDB) is a solution that allows users to retrieve data from databases in natural language. Various studies were conducted to translate Indonesian sentences into database queries, but these studies still have weaknesses. In this study, we propose the translation of interrogative sentences in the temporal database accompanied by the addition of several components that can improve the ability of NLIDB. The translation process is carried out by first masking the input sentence and decomposing the sentence into a collection of syntax trees. Then, the existing parsing tree is selected and the best parsing tree will be selected. Then, the process is continued with the analysis of the query components in the interrogative sentences. The results of the analysis will be translated into parts of database query and parts of database query will be rearranged into database queries. This query will be executed and the result can be evaluated by the user and the user can provide feedback according to the system output. The built NLIDB system can translate interrogative sentences for what, who, when, where, how, if, and how many questions with the types of queries that can be handled are current state, time-slice, sequenced, and non-sequenced.