Automatic formation of questions and answers on the basis of the knowledge base

Assel Omarbekova, Gulbarshyn Nurgazinova, Altynbek Sharipbay, Alibek Barlybayev, Gulmira Bekmanova

2017

Closed access Metadata (CSL-JSON)
DOI 10.1109/icengtechnol.2017.8308192
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This paper describes the process development for automatic generation of test questions and answers to the given questions from the knowledge base. The work products are application-oriented and will be used in the organization and arranging the smart learning. It is provided detailed examples of the ontology based representation models and the SPARQL query evaluation in RDF-documents. Also program implementation of issues generating program in the Python programming language with connecting the necessary libraries for working with RDF-files has been described.