On the relationship between bug reports and queries for text retrieval-based bug localization

Mills, Chris; Parra, Esteban; Pantiuchina, Jevgenija; Bavota, Gabriele; Haiduc, Sonia

doi:10.1007/s10664-020-09823-w

Cited by 25 publications

(57 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture of BERT consists of multiple layers of transformerencoders, which are an abstraction aimed at modeling sequential data that utilizes self-attention; the notion of attention is to weight specific terms in the sequence differently, i.e., encoding a stronger relationship from each term in the sequence to the remaining most semantically relevant terms. As pointed out by Mills et al [32], retrieval techniques for bug localization can be significantly improved with intelligent query construction, i.e., by carefully choosing which parts of the bug report to use for comparison. Therefore, leveraging a model that uses attention to emphasize certain word relationships has the potential to significantly improve upon prior state-of-the-art bug localization techniques.…”

Section: Bert For Bug Localizationmentioning

confidence: 99%

“…VSM-based techniques are likely to perform well on such bug reports, though localizing them may not be as useful to developers [48]. Mills et al refute the idea that VSM-based bug localization are significantly aided by hints, and note that VSM can perform well for bug localization if more attention is paid to how the query is constructed from the bug report text [32]. However, their findings do not preclude additional accuracy improvements by using more complex, semantic models, such as BERT.…”

Section: Code Element-based Bug Localizationmentioning

confidence: 99%

“…Automatically linking a bug report in a bug tracker and related software artifacts from a repository is one of the long-standing goals in the software engineering research community, due to its potential to improve practice by reducing the time developers spend examining code when addressing a newly reported bug, i.e., bug localization [35,62]. However, despite numerous efforts, the accuracy of bug localization approaches is not yet high enough for widespread use, especially as it applies to different software projects that vary in bug report and code style [32]. In examining the trends from interviews conducted with a large cohort of software developers from industry and open-source software, Zou et al report that developers do not trust bug localization tools due to their inability to adapt to different types of bug reports, specifically noting that existing techniques only work on the most simple cases, with straightforward textual similarity between the bug report and code base [64].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Fast Changeset-based Bug Localization with BERT

Ciborowska¹,

Damevski²

2021

Preprint

View full text Add to dashboard Cite

Automatically localizing software bugs to the changesets that induced them has the potential to improve software developer efficiency and to positively affect software quality. To facilitate this automation, a bug report has to be effectively matched with source code changes, even when a significant lexical gap exists between natural language used to describe the bug and identifier naming practices used by developers. To bridge this gap, we need techniques that are able to capture software engineering-specific and project-specific semantics in order to detect relatedness between the two types of documents that goes beyond exact term matching. Popular transformer-based deep learning architectures, such as BERT, excel at leveraging contextual information, hence appear to be a suitable candidate for the task. However, BERT-like models are computationally expensive, which precludes them from being used in an environment where response time is important.In this paper, we describe how BERT can be made fast enough to be applicable to changeset-based bug localization. We also explore several design decisions in using BERT for this purpose, including how best to encode changesets and how to match bug reports to individual changes for improved accuracy. We compare the accuracy and performance of our model to a non-contextual baseline (i.e., vector space model) and BERT-based architectures previously used in software engineering. Our evaluation results demonstrate advantages in using the proposed BERT model compared to the baselines, especially for bug reports that lack any hints about related code elements.

show abstract

Section: Bert For Bug Localizationmentioning

confidence: 99%

Section: Code Element-based Bug Localizationmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Fast Changeset-based Bug Localization with BERT

Ciborowska¹,

Damevski²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Section: Ir Based Approachmentioning

confidence: 99%

“…Some studies also focus on the query aspect of bug reports in the context of bug localization [44,45]. Chris et al [44] argue that better query can be formulated using the bug report, which can help achieve better results for IR based approaches. FineLocator performed methodlevel bug localization by considering three query expansion scores to address the "representation sparseness problem" of a function in the source code [45].…”

Section: Ir Based Approachmentioning

confidence: 99%

DRAST -- A Deep Learning and AST Based Approach for Bug Localization

Sangle,

Muvva,

Chimalakonda

et al. 2020

Preprint

View full text Add to dashboard Cite

Context: Given a bug report and source code of the project, bug localization can help developers to focus on fixing probable buggy files rather than searching the entire source code repository. While existing research uses information retrieval (IR) and/or combination of machine learning (ML) or deep learning (DL) approaches, they focus primarily on Java benchmark projects, and also motivate the need for multi-language bug localization approach.Objective: To create a novel bug localization approach that leverages the syntactic structure of source code, bug report information and which can support multi-language projects along with a new dataset of C projects.Method: The proposed DRAST approach represents source code as code vectors by using its high-level AST and combines rVSM, an IR technique with ML/DL models such as Random Forest and Deep Neural Network regressor to rank the list of buggy files. We also use features such as textual similarity using IR techniques, lexical mismatch using DNNs, and history of the project using the metadata of BugC dataset.Results: We tested DRAST on seven projects from the BugC dataset, which consists of 2462 bug reports from 21 open-source C projects. The results show that DRAST can locate correct buggy files 90% of the time from top 1, 5, and 10 suggested files with MAP and MRR scores of above 90% for the randomly selected seven projects. We also tested DRAST on Tomcat and AspectJ, projects from benchmark dataset with better results at accuracy@1, MAP and MRR when compared with state-of-the-art.Conclusions: This paper presents a novel bug localization approach that works on C and Java projects and a bug localization C dataset along with a novel source code representation. The results for C projects using DRAST are promising and could motivate researchers/practitioners to focus on developing and creating multi-language bug localization approaches.

show abstract

An empirical study of the effectiveness of IR-based bug localization for large-scale industrial projects

Ming

et al. 2022

Empir Software Eng

View full text Add to dashboard Cite

On the relationship between bug reports and queries for text retrieval-based bug localization

Cited by 25 publications

References 41 publications

Fast Changeset-based Bug Localization with BERT

Fast Changeset-based Bug Localization with BERT

DRAST -- A Deep Learning and AST Based Approach for Bug Localization

An empirical study of the effectiveness of IR-based bug localization for large-scale industrial projects

Contact Info

Product

Resources

About