Teaching machines to understand data science code by semantic enrichment of dataflow graphs

TL;DR

This paper presents an AI system that enhances data science code with semantic understanding by enriching dataflow graphs using a new ontology language, aiding human comprehension and collaboration.

Contribution

It introduces a novel semantic enrichment algorithm for dataflow graphs and a new ontology language for modeling computer programs and data science concepts.

Findings

Developed an algorithm for semantic enrichment of dataflow graphs.

Created a new ontology language for program and data science modeling.

Focused on code written by data scientists within open science initiatives.

Abstract

Your computer is continuously executing programs, but does it really understand them? Not in any meaningful sense. That burden falls upon human knowledge workers, who are increasingly asked to write and understand code. They deserve to have intelligent tools that reveal the connections between code and its subject matter. Towards this prospect, we develop an AI system that forms semantic representations of computer programs, using techniques from knowledge representation and program analysis. To create the representations, we introduce an algorithm for enriching dataflow graphs with semantic information. The semantic enrichment algorithm is undergirded by a new ontology language for modeling computer programs and a new ontology about data science, written in this language. Throughout the paper, we focus on code written by data scientists and we locate our work within a larger movement towards collaborative, open, and reproducible science.