An Empirical Study of IR-based Bug Localization for Deep Learning-based Software

Kim, Misoo; Kim, Young-Kyoung; Lee, Eunseok

doi:10.1109/icst53961.2022.00024

Cited by 2 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, a thorough overview of bug localization models [11,22] shows the effects of increasing components on bug localization performance. Our model correlates well with this hypothesis: AttentiveBugLocator (Siam+Attn+IR) shows the best performance on all data sets.…”

Section: Why Does Attentivebuglocator Work?mentioning

confidence: 99%

“…Several techniques have been proposed in the past to locate buggy source files with respect to user bug reports based on IR, topic modeling, and machine learning [11].…”

Section: Related Workmentioning

confidence: 99%

“…To further improve the effectiveness of bug localization models, recent studies proposed stack trace analysis, POS tagging and code segmentation to improve query quality [11].…”

Section: Related Workmentioning

confidence: 99%

“…Previously, several techniques have been proposed to locate buggy source files (SF s) with respect to user bug reports (BRs). These techniques are largely based on Information Retrieval (IR) methods such as Vector Space modeling (VSM), Latent Dirichlet allocation (LDA), and Latent Semantic Index (LSI) [19,37,11]. This way, a bug report is used as a query to return the relevant source files based on keywords matching or textual similarity.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

AttentiveBugLocator: A Bug Localization Model using Attention-based SemanticFeatures and Information Retrieval

Ahmad,

Yu,

Kholief

et al. 2023

Preprint

View full text Add to dashboard Cite

In recent years, deep learning-based algorithms such as CNN, LSTM, and autoencoders have been proposed to rank suspicious buggy files. Meanwhile,representational learning has served to be the best approach to extract rich semantic features of bug reports and source code to reduce their lexical mismatch. In this paper, we propose AttentiveBugLocator, a Siamese-based representational learning modelfor improved bug localization performance. AttentiveBugLocator employs BERT and code2vec embedding models to produce richer semantic representations and a Siamese BiLSTM network with context attention to learn semantic matching between BRs and SFs. To further improve the effectiveness of AttentiveBugLocator, the semantic matching features are carefully fused with VSM, stack trace, and code complexity features. Evaluation results on four data sets show that AttentiveBugLocator can identify buggy files on the scale of 56% and 62% on MAP and MRR – thus, outperforms several state-of-the-art approaches.

show abstract

Section: Why Does Attentivebuglocator Work?mentioning

confidence: 99%

“…Several techniques have been proposed in the past to locate buggy source files with respect to user bug reports based on IR, topic modeling, and machine learning [11].…”

Section: Related Workmentioning

confidence: 99%

“…To further improve the effectiveness of bug localization models, recent studies proposed stack trace analysis, POS tagging and code segmentation to improve query quality [11].…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations