Methodology for creating natural language interfaces to information systems in a specific domain area
Mariya Zhekova, George Totkov, George Pashev · 2022 International Conference on Electrical, Computer and Energy Technologies (ICECET) · 2022
The research is a crossroads in the fields of Informatics and Computational Linguistics and illustrates the understanding and interpretation of texts in natural language by computers. The focus of the research is the presented methodology for describing domain area. In it, the computer is trained with the help of grammar rules and storage (classified linguistic corpus) of possible word combinations of language units, presented and characterized as relevant grammar classes. The proposed methodology for describing a domain area (DA) is part of a process of creating natural language interface (NLI), which uses existing tools, instruments and approaches, further developed and modified to extract answers from databases of different information systems in the same DA. The components obtained as a result of the steps in the proposed methodology (a model of concepts for the DA, upgraded with their lexical characteristics and relationships between them) are sufficient for the NLI to function and return an answer to a question to the IS.