Write a Blog >>
ICSE 2021
Mon 17 May - Sat 5 June 2021

Software traceability establishes and leverages associations between diverse development artifacts. Researchers have proposed the use of deep learning trace models to link natural language artifacts, such as requirements and issue descriptions, to source code; however, their effectiveness has been restricted by the availability of labeled data and efficiency at runtime. In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts. To address data sparsity, we leverage a three-step training strategy to enable trace models to transfer knowledge from a closely related Software Engineering challenge, which has a rich dataset, to produce trace links with much higher accuracy than has previously been achieved. We then apply the T-BERT framework to recover links between issues and commits in Open Source Projects. We comparatively evaluated the accuracy and efficiency of three BERT architectures in the framework. Experimental results show that a Single-BERT architecture generated the most accurate links, while a Siamese-BERT architecture produced comparable results with significantly less execution time. Furthermore, by learning and transferring knowledge, all three models in the framework can far outperform classical IR trace models and achieve impressive tracing accuracy on real-word OSS projects.

Conference Day
Tue 25 May

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

15:20 - 16:15
1.3.2. Deep Neural Networks: Supporting SE Tasks #1NIER - New Ideas and Emerging Results / Journal-First Papers / Technical Track at Blended Sessions Room 2 +12h
Chair(s): Ayse TosunIstanbul Technical University
15:20
20m
Paper
CODIT: Code Editing with Tree-Based Neural ModelsJournal-First
Journal-First Papers
Saikat ChakrabortyColumbia University, Yangruibo DingColumbia University, Miltiadis AllamanisMicrosoft Research, UK, Baishakhi RayColumbia University, USA
Link to publication DOI Pre-print Media Attached
15:40
20m
Paper
Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT ModelsACM SIGSOFT Distinguished PaperTechnical Track
Technical Track
Jinfeng LinUniversity of Notre Dame, Yalin LiuUniversity of Notre Dame, Qingkai ZengUniversity of Notre Dame, Meng JiangUniversity of Notre Dame, Jane Cleland-HuangUniversity of Notre Dame
Pre-print Media Attached
16:00
15m
Paper
A Cognitive and Machine Learning-Based Software Development Paradigm Supported by ContextNIER
NIER - New Ideas and Emerging Results
Glaucia MeloUniversity of Waterloo, Paulo AlencarUniversity of Waterloo, Don CowanUniversity of Waterloo
Pre-print Media Attached

Conference Day
Wed 26 May

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

03:20 - 04:15
03:20
20m
Paper
CODIT: Code Editing with Tree-Based Neural ModelsJournal-First
Journal-First Papers
Saikat ChakrabortyColumbia University, Yangruibo DingColumbia University, Miltiadis AllamanisMicrosoft Research, UK, Baishakhi RayColumbia University, USA
Link to publication DOI Pre-print Media Attached
03:40
20m
Paper
Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT ModelsACM SIGSOFT Distinguished PaperTechnical Track
Technical Track
Jinfeng LinUniversity of Notre Dame, Yalin LiuUniversity of Notre Dame, Qingkai ZengUniversity of Notre Dame, Meng JiangUniversity of Notre Dame, Jane Cleland-HuangUniversity of Notre Dame
Pre-print Media Attached
04:00
15m
Paper
A Cognitive and Machine Learning-Based Software Development Paradigm Supported by ContextNIER
NIER - New Ideas and Emerging Results
Glaucia MeloUniversity of Waterloo, Paulo AlencarUniversity of Waterloo, Don CowanUniversity of Waterloo
Pre-print Media Attached