A System-Wide Debugging Assistant Powered by Natural Language Processing

Pradeep Dogga; Karthik Narasimhan; Anirudh Sivaraman; Ravi Netravali

doi:10.1145/3357223.3362701

A System-Wide Debugging Assistant Powered by Natural Language Processing

Pradeep Dogga, Karthik Narasimhan, Anirudh Sivaraman, Ravi Netravali

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

6 Scopus citations

Abstract

Despite advances in debugging tools, systems debugging today remains largely manual. A developer typically follows an iterative and time-consuming process to move from a reported bug to a bug fix. This is because developers are still responsible for making sense of system-wide semantics, bridging together outputs and features from existing debugging tools, and extracting information from many diverse data sources (e.g., bug reports, source code, comments, documentation, and execution traces). We believe that the latest statistical natural language processing (NLP) techniques can help automatically analyze these data sources and significantly improve the systems debugging experience. We present early results to highlight the promise of NLP-powered debugging, and discuss systems and learning challenges that must be overcome to realize this vision.

Original language	English (US)
Title of host publication	SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing
Publisher	Association for Computing Machinery
Pages	171-177
Number of pages	7
ISBN (Electronic)	9781450369732
DOIs	https://doi.org/10.1145/3357223.3362701
State	Published - Nov 20 2019
Event	10th ACM Symposium on Cloud Computing, SoCC 2019 - Santa Cruz, United States Duration: Nov 20 2019 → Nov 23 2019

Publication series

Name	SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing

Conference

Conference	10th ACM Symposium on Cloud Computing, SoCC 2019
Country/Territory	United States
City	Santa Cruz
Period	11/20/19 → 11/23/19

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computational Theory and Mathematics

Keywords

natural language processing
systems debugging

Access to Document

10.1145/3357223.3362701

Cite this

@inproceedings{2430b134cdff4c72b5524225b24f212a,

title = "A System-Wide Debugging Assistant Powered by Natural Language Processing",

abstract = "Despite advances in debugging tools, systems debugging today remains largely manual. A developer typically follows an iterative and time-consuming process to move from a reported bug to a bug fix. This is because developers are still responsible for making sense of system-wide semantics, bridging together outputs and features from existing debugging tools, and extracting information from many diverse data sources (e.g., bug reports, source code, comments, documentation, and execution traces). We believe that the latest statistical natural language processing (NLP) techniques can help automatically analyze these data sources and significantly improve the systems debugging experience. We present early results to highlight the promise of NLP-powered debugging, and discuss systems and learning challenges that must be overcome to realize this vision.",

keywords = "natural language processing, systems debugging",

author = "Pradeep Dogga and Karthik Narasimhan and Anirudh Sivaraman and Ravi Netravali",

note = "Publisher Copyright: {\textcopyright} 2019 ACM.; 10th ACM Symposium on Cloud Computing, SoCC 2019 ; Conference date: 20-11-2019 Through 23-11-2019",

year = "2019",

month = nov,

day = "20",

doi = "10.1145/3357223.3362701",

language = "English (US)",

series = "SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing",

publisher = "Association for Computing Machinery",

pages = "171--177",

booktitle = "SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing",

}

Dogga, P, Narasimhan, K, Sivaraman, A & Netravali, R 2019, A System-Wide Debugging Assistant Powered by Natural Language Processing. in SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing. SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing, Association for Computing Machinery, pp. 171-177, 10th ACM Symposium on Cloud Computing, SoCC 2019, Santa Cruz, United States, 11/20/19. https://doi.org/10.1145/3357223.3362701

A System-Wide Debugging Assistant Powered by Natural Language Processing. / Dogga, Pradeep; Narasimhan, Karthik; Sivaraman, Anirudh et al.
SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing. Association for Computing Machinery, 2019. p. 171-177 (SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing).

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

TY - GEN

T1 - A System-Wide Debugging Assistant Powered by Natural Language Processing

AU - Dogga, Pradeep

AU - Narasimhan, Karthik

AU - Sivaraman, Anirudh

AU - Netravali, Ravi

PY - 2019/11/20

Y1 - 2019/11/20

N2 - Despite advances in debugging tools, systems debugging today remains largely manual. A developer typically follows an iterative and time-consuming process to move from a reported bug to a bug fix. This is because developers are still responsible for making sense of system-wide semantics, bridging together outputs and features from existing debugging tools, and extracting information from many diverse data sources (e.g., bug reports, source code, comments, documentation, and execution traces). We believe that the latest statistical natural language processing (NLP) techniques can help automatically analyze these data sources and significantly improve the systems debugging experience. We present early results to highlight the promise of NLP-powered debugging, and discuss systems and learning challenges that must be overcome to realize this vision.

AB - Despite advances in debugging tools, systems debugging today remains largely manual. A developer typically follows an iterative and time-consuming process to move from a reported bug to a bug fix. This is because developers are still responsible for making sense of system-wide semantics, bridging together outputs and features from existing debugging tools, and extracting information from many diverse data sources (e.g., bug reports, source code, comments, documentation, and execution traces). We believe that the latest statistical natural language processing (NLP) techniques can help automatically analyze these data sources and significantly improve the systems debugging experience. We present early results to highlight the promise of NLP-powered debugging, and discuss systems and learning challenges that must be overcome to realize this vision.

KW - natural language processing

KW - systems debugging

UR - http://www.scopus.com/inward/record.url?scp=85084648842&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084648842&partnerID=8YFLogxK

U2 - 10.1145/3357223.3362701

DO - 10.1145/3357223.3362701

M3 - Conference contribution

AN - SCOPUS:85084648842

T3 - SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing

SP - 171

EP - 177

BT - SoCC 2019 - Proceedings of the ACM Symposium on Cloud Computing

PB - Association for Computing Machinery

T2 - 10th ACM Symposium on Cloud Computing, SoCC 2019

Y2 - 20 November 2019 through 23 November 2019

ER -

A System-Wide Debugging Assistant Powered by Natural Language Processing

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this