Abstract
This article describes construction and investigation the mathematical model of natural query language translation with using an abstract query language. Abstract query language allows separating the problem of the processing natural language texts with using the linguistic knowledge from a problem of generation target query. Separation these tasks enables the construction modular natural language interface, which will be determined the same time translation algorithms to different sources of structured data in different target language queries using subsets of linguistic knowledge bases describing the desired subject area. In the proposed mathematical model is given a way to describe the concepts and relationships between them. With the help of concepts and relations between them, determined the linguistic knowledge base is used in the algorithm of translation. So, conversion of NL-queries to the abstract queries is reduced to sequential application of constructs for the purpose of separation from NL-queries of concepts of data domain, their components and the relations in between and to display of the selected concepts to a data model of the target structured data source.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
