TeKnowbase: Towards Construction of a Knowledge-base of Technical Concepts

TL;DR

TeKnowbase is a large, accurate knowledge-base of computer science concepts built from online sources, improving technical concept classification tasks.

Contribution

This work introduces TeKnowbase, a comprehensive knowledge-base of technical concepts with high accuracy, constructed from multiple online sources, and demonstrates its utility in classification tasks.

Findings

Knowledge-base contains approximately 100,000 triples.

Achieved over 90% accuracy in triple evaluation.

Improved classification accuracy on StackOverflow data.

Abstract

In this paper, we describe the construction of TeKnowbase, a knowledge-base of technical concepts in computer science. Our main information sources are technical websites such as Webopedia and Techtarget as well as Wikipedia and online textbooks. We divide the knowledge-base construction problem into two parts -- the acquisition of entities and the extraction of relationships among these entities. Our knowledge-base consists of approximately 100,000 triples. We conducted an evaluation on a sample of triples and report an accuracy of a little over 90\%. We additionally conducted classification experiments on StackOverflow data with features from TeKnowbase and achieved improved classification accuracy.