A deep multimodal model for bug localization

Zhu, Ziye; Li, Yun; Wang, Yu; Wang, Yaojin; Tong, Hanghang

doi:10.1007/s10618-021-00755-7

Cited by 14 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, as noted earlier, recent papers (Qi et al, 2021;Zhu et al, 2021;Zhang et al, 2020a) employed attention mechanism to improve bug localization accuracy. However, these models rarely visualize the feature segments from attention units to understand and select input segment.…”

Section: Bug Localizationmentioning

confidence: 80%

“…In this case, RNN has been utilized to extract structural features from word embedding vectors and CNN features. For example, a recent paper (Zhu, Li, Wang, Wang and Tong, 2021) proposed a combined network of BiLSTM and DCNN to learn peculiar semantic and sequential information from natural language and programming language representations of bug reports and source codes.…”

Section: Bug Localizationmentioning

confidence: 99%

“…Similarly, attention mechanism has been increasingly used to improve the feature extraction power of sequence models. Specifically, in BugTranslator, an attention based Transformer model (Xiao, Keung, Bennin and Mi, 2018a;Xiao, Pan, Zhang, Hu, Li and Lu, 2021), and attention-BiLSTM (Qi, Sun, Yuan, Zhang and Meng, 2021;Zhu et al, 2021;Loyola et al, 2018;Zhang et al, 2020a) in order to extract semantic and structural information, code changes dependency, code specific attention, and bug specific attention from bug report and source code tokens. In these papers, the attention-based features improved bug localization accuracy by extracting most important information.…”

Section: Bug Localizationmentioning

confidence: 99%

See 2 more Smart Citations

Deep Bug Reports Processing (DBRP): A Systematic Literature Review

Ahmad

Kholief

et al. 2023

Preprint

View full text Add to dashboard Cite

Many software projects utilize Bug Tracking System (BTS) to manage and process bug reports. Over the years, the number of bug report submissions has increased exponentially with some projects receiving as many as about a hundred submissions daily. Bug report processing (BRP) consists of five key processes: duplicate detection, severity prediction, fix-time prediction, bug triage, and bug localization. Previously, traditional machine learning (ML) algorithms -based models were proposed to automate BRP tasks. However, in recent years deep BRP (DBRP) models were proposed to exploit the ever-increasing bug repositories for automatic extraction of semantic and contextual features of bug reports. Although, some papers reviewed related literature from many perspectives of software maintenance, no existing work comprehensively reviewed the state of DBRP. In this paper, we review the state of DBRP models in the five key BRP tasks. For this, we collect papers from four international databases published between 2015 and 2021. We evaluate the papers with regard to the deep neural networks, text representation models, and bug report features utilized. Finally, we present findings and prospects for future research works in DBRP. Our review analyzes how word embedding, CNNs, LSTMs, attention mechanism are used to represent bug report and source code, model performance and challenges such as data imbalance, feature utilization and complexity.

show abstract

Section: Bug Localizationmentioning

confidence: 80%

Section: Bug Localizationmentioning

confidence: 99%

Section: Bug Localizationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Bug Reports Processing (DBRP): A Systematic Literature Review

Ahmad

Kholief

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Hybrid system model [13][14][15][16][17][18][19][20] Evaluation of system working conditions Control system model [21][22][23][24][25][26][27] System fault model Coldbox model [28][29][30][31] Evaluation of system fault conditions Hotbox model -In addition, the SOFC system fault is usually not sudden, but gradually evolves through the changes of system multiple transition phases in long-term abnormal operation [32,33]. There are multiple modes in the operation of any equipment, and there are also multiple modes in SOFC system.…”

Section: System Modelmentioning

confidence: 99%

Modeling Analysis of SOFC System Oriented to Working Condition Identification

Zhang

Liu

et al. 2022

Energies

View full text Add to dashboard Cite

Solid oxide fuel cell (SOFC) generation system is an important equipment to realize “carbon neutralization”. In SOFC system, a fault will cause changes in working conditions, which is difficult to detect early and find the reason due to the high temperature and seal environment. Therefore, the mechanistic model is a feasible way to find the reasons for the change of system working conditions. In this paper, based on the first law of thermodynamics, the system model of SOFC is built under multiple working conditions, and the influence of stack, afterburner, heat exchanger, and reformer fault is studied on the thermoelectric characteristics and efficiency of the system. The results show that with the introduction of these fault mechanistic models, the dynamic response characteristics of SOFC system under multiple working conditions can be obtained by tracking the key performance parameters qualitatively. The work of this paper is helpful for the guidance of the fault diagnosis of SOFC system in the future.

show abstract

“…Many different artifacts (e.g., bug reports, source code files) are created during software development and maintenance of one software project. Program failures or defects are recorded on bug reports by different stakeholders (e.g., end-users, developers, or testers) (ZHU et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Heterogeneous information network to support the bug report resolution process

Barbosa¹

View full text Add to dashboard Cite

Contexto. Ao longo do ciclo de vida de um software, inúmeros documentos (por exemplo, relatórios de incidentes e código fonte) são produzidos por stakeholders. Os relatórios de incidentes (RI) são os principais documentos de insumo para apoiar as atividades (predição da severidade de relatórios de incidentes e recomendação de responsáveis pela correção do software) do processo de resolução de relatórios de incidentes (RRI). Já o código fonte combinado com os relatórios de incidentes são insumos para apoiar atividades de localização de defeitos. A Automação dessas atividades do processo RRI requer uma preocupação em como obter uma representação semanticamente representativa. Tradicionalmente utiliza-se Bag-of-Word (BoW) para representar os documentos de software para apoiar a execução automática dessas atividades por meio de algoritmos de aprendizado de máquina. Lacuna. No entanto, pouca atenção foi dada para representações baseadas em redes de informações heterogêneas (RIH), que permitem representar redes complexas respeitando os relacionamentos entre diferentes objetos. Contribuição. Esta tese de doutorado contribui para o avanço do estado da arte no que se refere aos modelos de representação de informações para apoiar a execução automática de atividades do processo RRI. Também avança na investigação de (i) algoritmos semissupervisionados que utilizam redes heterogêneas bipartidas para apoiar a predição de severidade de RI, (ii) um método que combina a representação BoW e redes de informações heterogêneas para apoiar a atividade de localização de defeitos, e (iii) uma abordagem holística que reutilizar uma rede de informações heterogêneas para apoiar atividades de RRI. Resultados. Os resultados demonstram que redes de informações heterogêneas podem ser uma alternativa promissora para apoiar a automação do processo RRI. Conclusões. Um processo RRI automático numa perspectica holística utilizando rede de informações heterogêneas apresentou resultados promissores ao serem comparados com representações do estado da arte.

show abstract

A deep multimodal model for bug localization

Cited by 14 publications

References 35 publications

Deep Bug Reports Processing (DBRP): A Systematic Literature Review

Deep Bug Reports Processing (DBRP): A Systematic Literature Review

Modeling Analysis of SOFC System Oriented to Working Condition Identification

Heterogeneous information network to support the bug report resolution process

Contact Info

Product

Resources

About