From natural language to graph queries








Abstract

Automatic code generation can drastically improve software (SW) engineering and SW development projects. In the last decade we have been conducting research which has been advancing the field of code generators for small and mid-size Web-based DBMS systems [4], [5], [7]. We developed a number of tool prototypes for automatic source code debugging by the source-to-source code transformation for real C and C++ applications [8]. Additionally we investigated Natural Language Processing (NLP) for software code generation and application of it to Graph databases. Graph databases are becoming more and more popular for their applications in Artificial Intelligence (AI) systems, social analytics and many other fields. Query languages like Cypher allow users to search them without direct programming. But even queries of modest complexity like “relatives in a family & friends graph” require some skill to write. In this paper we describe the use of natural language as a more intuitive interface for untrained users and demonstrate 3 use-cases, where translation of typical English phrases to OpenCypher and/or specialized graph engines like Huawei EYWA.


Modules


Algorithms


Software And Hardware

• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL