Issue Report Classification Using Pre-trained Language Models

被引：13

作者：

Colavito, Giuseppe ^{[1
]}

Lanubile, Filippo ^{[1
]}

Novielli, Nicole ^{[1
]}

机构：

[1] Univ Bari, Bari, Italy

来源：

2022 IEEE/ACM 1ST INTERNATIONAL WORKSHOP ON NATURAL LANGUAGE-BASED SOFTWARE ENGINEERING (NLBSE 2022) | 2022年

关键词：

Issue classification; BERT; deep learning; labeling unstructured data; software maintenance and evolution;

D O I：

10.1145/3528588.3528659

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes our participation in the tool competition organized in the scope of the 1st International Workshop on Natural Language-based Software Engineering. We propose a supervised approach relying on fine-tuned BERT-based language models for the automatic classification of GitHub issues. We experimented with different pre-trained models, achieving the best performance with fine-tuned RoBERTa (F1 = .8591).

引用

页码：29 / 32

页数：4

共 17 条

[1]

Antoniol Giuliano, 2008, P C CTR ADV STUD COL, DOI DOI 10.1145/1463788.1463819

[2] BERT-Based Sentiment Analysis: A Software Engineering Perspective [J].

Batra, Himanshu ;

Punn, Narinder Singh ;

Sonbhadra, Sanjay Kumar ;

Agarwal, Sonali .

DATABASE AND EXPERT SYSTEMS APPLICATIONS, DEXA 2021, PT I, 2021, 12923 :138-148

[3] Achieving Reliable Sentiment Analysis in the Software Engineering Domain using BERT [J].

Biswas, Eeshita ;

Karabulut, Mehmet Efruz ;

Pollock, Lori ;

Vijay-Shanker, K. .

2020 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE AND EVOLUTION (ICSME 2020), 2020, :162-173

[4]

Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171

[5]

Giuseppe Colavito, 2022, ISSUE REPORT CLASSIF

[6] Predicting the objective and priority of issue reports in software repositories [J].

Izadi, Maliheh ;

Akbari, Kiana ;

Heydarnoori, Abbas .

EMPIRICAL SOFTWARE ENGINEERING, 2022, 27 (02)

[7]

Joulin Armand., 2017, EACL, V2017, P427

[8] Predicting issue types on GitHub [J].

Kallis, Rafael ;

Di Sorbo, Andrea ;

Canfora, Gerardo ;

Panichella, Sebastiano .

SCIENCE OF COMPUTER PROGRAMMING, 2021, 205

[9] Ticket Tagger: Machine Learning Driven Issue Classification [J].

Kallis, Rafael ;

Di Sorbo, Andrea ;

Canfora, Gerardo ;

Panichella, Sebastiano .

2019 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE AND EVOLUTION (ICSME 2019), 2019, :406-409

[10]

Kallis Rafael, 2022, P 1 INT WORKSHOP NAT

← 1 2 →