EASE 2024
Tue 18 - Fri 21 June 2024 Salerno, Italy
Thu 20 Jun 2024 11:30 - 11:45 at Room Vietri - Mining Software Repositories Chair(s): Giuseppe Destefanis

Machine Translation (MT) has numerous applications in Software Engineering (SE). Recently, it has been employed not only for programming language translation but also as an oracle for deriving information for various research problems in SE. In this application branch, MT’s impact has been assessed through metrics measuring the accuracy of these problems rather than traditional translation evaluation metrics. For code search, a recent work, ASTTrans, introduced an MT-based model for extracting relevant non-terminal nodes from the Abstract Syntax Tree (AST) of an implementation based on natural language descriptions. While ASTTrans demonstrated the effectiveness of MT in enhancing code search on small datasets with low embedding dimensions, it struggled to improve the accuracy of code search on the standard benchmark CodeSearchNet. In this work, we present Oracle4CS, a novel approach that integrates the classical MT model called Statistical Machine Translation to support modernized models for code search. To accomplish this, we introduce a new code representation technique called ASTSum, which summarizes each code snippet using a limited number of AST nodes. Additionally, we devise a fresh approach to code search, replacing natural language queries with a new representation that incorporates the results of our query-to-ASTSum translation process. Through experiments, we demonstrate that Oracle4CS can enhance code search performance on both the original BERT-based model UniXcoder and the optimized BERT-based model CoCoSoDa by up to 1.18% and 2% in Mean Reciprocal Rank (MRR) across eight selected well-known datasets. We also explore ASTSum as a promising code representation for supporting code search, potentially improving MRR by over 17% on average when paired with an optimal SMT model for query-to-ASTSum translation.

Thu 20 Jun

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

11:00 - 12:30
Mining Software RepositoriesResearch Papers / Journal-first at Room Vietri
Chair(s): Giuseppe Destefanis Brunel University London
11:00
15m
Talk
On the Accuracy of GitHub's Dependency Graph
Research Papers
Daniele Bifolco University of Sannio, Sabato Nocera Department of Computer Science, University of Salerno, Simone Romano University of Salerno, Massimiliano Di Penta University of Sannio, Italy, Rita Francese University of Salerno, Giuseppe Scanniello University of Salerno
11:15
15m
Talk
Towards Semi-Automated Merge Conflict Resolution: Is It Easier Than We Expected?Distinguished Paper Award
Research Papers
Alexander Boll University of Bern, Yael van Dok University of Bern, Manuel Ohrndorf University of Bern, Alexander Schultheiß Paderborn University, Timo Kehrer University of Bern
11:30
15m
Talk
Leveraging Statistical Machine Translation for Code Search
Research Papers
Hung Phan , Ali Jannesari Iowa State University
11:45
15m
Talk
LEGION: Harnessing Pre-trained Language Models for GitHub Topic Recommendations with Distribution-Balance Loss
Research Papers
Yen-Trang Dang Hanoi University of Science and Technology, Le-Cong Thanh The University of Melbourne, Phuc-Thanh Nguyen Hanoi University of Science and Technology, Anh M. T. Bui Hanoi University of Science and Technology, Phuong T. Nguyen University of L’Aquila, Xuan-Bach D. Le University of Melbourne, Quyet Thang Huynh Hanoi University of Science and Technology
Pre-print
12:00
15m
Talk
LLM-Based Chatbots for Mining Software Repositories: Challenges and Opportunities
Research Papers
Samuel Abedu Concordia University, Ahmad Abdellatif University of Calgary, Emad Shihab Concordia University
Pre-print
12:15
15m
Talk
An exploratory study of software artifacts on GitHub from the lens of documentation
Journal-first
Akhila Sri Manasa Venigalla IIT Tirupati, Sridhar Chimalakonda Indian Institute of Technology, Tirupati