NLP Relational Queries and Its Application

Abstract

Recent advances in natural language processing have shown the effectiveness of statistical and neural networkbased algorithms in a deep understanding of textual data. We demonstrate that the result of NLP analysis on text documents can enrich relational data in a way so that structured queries can be used to derive further value from text data. In this paper, we present how we can perform analytics on a scientific research dataset based on both the relational data and NLP topic modeling. The integrated NLP features together with the classical relational query constructs allow one to explore the topic structure of the DBLP dataset with flexibility and precision.