RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning

Christopher Williams; Rosa Filgueira

doi:10.1109/e-Science58273.2023.10254843

RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning

Christopher Williams, Rosa Filgueira^*

^*Corresponding author for this work

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This work presents RepoGraph, an integrated semantic code exploration web tool that combines information extraction, knowledge graphs, and deep learning models. It offers new capabilities for software developers (from academia and industry) to represent and query Python repositories. Unlike existing tools, RepoGraph not only provides a novel search interface powered by deep learning techniques but also exposes the underlying features and representations of repositories to users. Additionally, it offers several interactive visualizations. We also introduce RepoPyOnto, a new ontology that captures the features of Python code repositories and is used by RepoGraph for representing the captured knowledge. Finally, we successfully evaluate RepoGraph against several criteria, including function summarization performance, the correctness and relevance of search results, as well as the processing time for constructing graphs of various sizes.

Original language	English
Title of host publication	Proceedings
Subtitle of host publication	2023 IEEE 19th international conference on e-science (e-science)
Editors	George Angelos Papadopoulos, Rosa Filgueira, Rafael Ferreira Da Silva
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	10
ISBN (Electronic)	9798350322231
ISBN (Print)	9798350322248
DOIs	https://doi.org/10.1109/e-Science58273.2023.10254843
Publication status	Published - 25 Sept 2023
Event	19th IEEE International Conference on eScience - Limassol, Cyprus, Limassol, Cyprus Duration: 9 Oct 2023 → 13 Oct 2023 Conference number: 19 https://www.escience-conference.org/2023/

Publication series

Name	IEEE international conference on e-science
ISSN (Print)	2325-372X
ISSN (Electronic)	2325-3703

Conference

Conference	19th IEEE International Conference on eScience
Abbreviated title	eScience
Country/Territory	Cyprus
City	Limassol
Period	9/10/23 → 13/10/23
Internet address	https://www.escience-conference.org/2023/

Keywords

Static code analysis
Code exploration
Code understanding
Semantic code search
Knowledge graph
Function summarization
Transfer learning
Deep learning models

Access to Document

10.1109/e-Science58273.2023.10254843

RepoGraph-submitted
Copyright © 2023 IEEE. This work has been made available online in accordance with publisher policies or with permission. Permission for further reuse of this content should be sought from the publisher or the rights holder. This is the author created accepted manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at https://doi.org/10.1109/e-Science58273.2023.10254843.
Accepted author manuscript, 7.01 MB

Cite this

Williams, C., & Filgueira, R. (2023). RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning. In G. A. Papadopoulos, R. Filgueira, & R. F. Da Silva (Eds.), Proceedings: 2023 IEEE 19th international conference on e-science (e-science) Article 10254843 (IEEE international conference on e-science). IEEE. https://doi.org/10.1109/e-Science58273.2023.10254843

Williams, Christopher ; Filgueira, Rosa. / RepoGraph : a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning. Proceedings: 2023 IEEE 19th international conference on e-science (e-science). editor / George Angelos Papadopoulos ; Rosa Filgueira ; Rafael Ferreira Da Silva. Piscataway, NJ : IEEE, 2023. (IEEE international conference on e-science).

@inproceedings{bbccdce758924cabae4642ae97263fb3,

title = "RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning",

abstract = "This work presents RepoGraph, an integrated semantic code exploration web tool that combines information extraction, knowledge graphs, and deep learning models. It offers new capabilities for software developers (from academia and industry) to represent and query Python repositories. Unlike existing tools, RepoGraph not only provides a novel search interface powered by deep learning techniques but also exposes the underlying features and representations of repositories to users. Additionally, it offers several interactive visualizations. We also introduce RepoPyOnto, a new ontology that captures the features of Python code repositories and is used by RepoGraph for representing the captured knowledge. Finally, we successfully evaluate RepoGraph against several criteria, including function summarization performance, the correctness and relevance of search results, as well as the processing time for constructing graphs of various sizes.",

keywords = "Static code analysis, Code exploration, Code understanding, Semantic code search, Knowledge graph, Function summarization, Transfer learning, Deep learning models",

author = "Christopher Williams and Rosa Filgueira",

year = "2023",

month = sep,

day = "25",

doi = "10.1109/e-Science58273.2023.10254843",

language = "English",

isbn = "9798350322248",

series = "IEEE international conference on e-science",

publisher = "IEEE",

editor = "Papadopoulos, {George Angelos} and Rosa Filgueira and {Da Silva}, {Rafael Ferreira}",

booktitle = "Proceedings",

note = "19th IEEE International Conference on eScience, eScience ; Conference date: 09-10-2023 Through 13-10-2023",

url = "https://www.escience-conference.org/2023/",

}

Williams, C & Filgueira, R 2023, RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning. in GA Papadopoulos, R Filgueira & RF Da Silva (eds), Proceedings: 2023 IEEE 19th international conference on e-science (e-science)., 10254843, IEEE international conference on e-science, IEEE, Piscataway, NJ, 19th IEEE International Conference on eScience, Limassol, Cyprus, 9/10/23. https://doi.org/10.1109/e-Science58273.2023.10254843

RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning. / Williams, Christopher; Filgueira, Rosa.
Proceedings: 2023 IEEE 19th international conference on e-science (e-science). ed. / George Angelos Papadopoulos; Rosa Filgueira; Rafael Ferreira Da Silva. Piscataway, NJ: IEEE, 2023. 10254843 (IEEE international conference on e-science).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - RepoGraph

T2 - 19th IEEE International Conference on eScience

AU - Williams, Christopher

AU - Filgueira, Rosa

N1 - Conference code: 19

PY - 2023/9/25

Y1 - 2023/9/25

N2 - This work presents RepoGraph, an integrated semantic code exploration web tool that combines information extraction, knowledge graphs, and deep learning models. It offers new capabilities for software developers (from academia and industry) to represent and query Python repositories. Unlike existing tools, RepoGraph not only provides a novel search interface powered by deep learning techniques but also exposes the underlying features and representations of repositories to users. Additionally, it offers several interactive visualizations. We also introduce RepoPyOnto, a new ontology that captures the features of Python code repositories and is used by RepoGraph for representing the captured knowledge. Finally, we successfully evaluate RepoGraph against several criteria, including function summarization performance, the correctness and relevance of search results, as well as the processing time for constructing graphs of various sizes.

AB - This work presents RepoGraph, an integrated semantic code exploration web tool that combines information extraction, knowledge graphs, and deep learning models. It offers new capabilities for software developers (from academia and industry) to represent and query Python repositories. Unlike existing tools, RepoGraph not only provides a novel search interface powered by deep learning techniques but also exposes the underlying features and representations of repositories to users. Additionally, it offers several interactive visualizations. We also introduce RepoPyOnto, a new ontology that captures the features of Python code repositories and is used by RepoGraph for representing the captured knowledge. Finally, we successfully evaluate RepoGraph against several criteria, including function summarization performance, the correctness and relevance of search results, as well as the processing time for constructing graphs of various sizes.

KW - Static code analysis

KW - Code exploration

KW - Code understanding

KW - Semantic code search

KW - Knowledge graph

KW - Function summarization

KW - Transfer learning

KW - Deep learning models

UR - https://doi.org/10.1109/e-Science58273.2023

U2 - 10.1109/e-Science58273.2023.10254843

DO - 10.1109/e-Science58273.2023.10254843

M3 - Conference contribution

SN - 9798350322248

T3 - IEEE international conference on e-science

BT - Proceedings

A2 - Papadopoulos, George Angelos

A2 - Filgueira, Rosa

A2 - Da Silva, Rafael Ferreira

PB - IEEE

CY - Piscataway, NJ

Y2 - 9 October 2023 through 13 October 2023

ER -

Williams C, Filgueira R. RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning. In Papadopoulos GA, Filgueira R, Da Silva RF, editors, Proceedings: 2023 IEEE 19th international conference on e-science (e-science). Piscataway, NJ: IEEE. 2023. 10254843. (IEEE international conference on e-science). doi: 10.1109/e-Science58273.2023.10254843

RepoGraph: a novel semantic code exploration tool for Python repositories based on knowledge graphs and deep learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this