Deep Transfer Bug Localization

Huo, Xuan; Thung, Ferdian; Li, Ming; Lo, David; Shi, Shuting

doi:10.1109/tse.2019.2920771

Cited by 60 publications

(36 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maybe only simple bugs?". To bridge this gap, researchers have recently proposed to use deep learning models capable of building semantically rich document representations [4,6,12,16,24,27,33]. Transformerbased models, and BERT in particular, are currently one of the most exciting deep learning techniques achieving broad improvements across a variety of text-based tasks.…”

Section: Problem Descriptionmentioning

confidence: 99%

“…The main opportunity in using FBL-BERT is in incorporating additional context and semantics when retrieving bug-inducing changesets, which should provide improvements in accuracy over the state-of-the-art, especially for bug reports that provide high level bug descriptions and lack explicit localization hints. Researchers have identified that a non-trivial amount of bug reports already contain localization hints, i.e., they mention the class or method names relevant to fixing the bug, and some recent approaches for bug localization argue that only bug reports that lack extensive localization hints should be considered in evaluation [17]. We follow the methodology proposed by Kochhar et al [23] to categorize bug reports into 3 groups based on the completeness of localization hints they provide and evaluate the performance for each bug report group separately.…”

Section: Experimental Evaluation 41 Research Questionsmentioning

confidence: 99%

“…More recently, software engineering researchers have been interested in the applying deep learning techniques towards bug localization. For instance, TRANP-CNN [17] is a recent technique that combines cross-project transfer learning and convolutional neural networks to achieve state-of-the-art performance on file-level bug localization. CooBa improves on TRANP-CNN by combining a shared encoder to capture cross-project with per-project features and using adversarial training to ensure that the per-project information remains unaffected by noise [63].…”

Section: Code Element-based Bug Localizationmentioning

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: Problem Descriptionmentioning

confidence: 99%

Section: Experimental Evaluation 41 Research Questionsmentioning

confidence: 99%

Section: Code Element-based Bug Localizationmentioning

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

“…Xuan et al [26] proposed a deep learning-based method for bug locating. The bug locating models proposed a ranked list of files based on the probability that a file is the source of the current bug.…”

Section: Related Workmentioning

confidence: 99%

Predicting the bug fixing time using word embedding and deep long short term memories

2020

View full text Add to dashboard Cite

In bug fixing process, estimating the 'Time to Fix Bug' is one of the factors that helps the triager to allocate jobs in a better way. Due to the limitation of resources for bug fixing, the bugs with long fixing time must be identified, as soon as possible, after receiving the report. This helps the prioritisation and fixing process of the bug reports. In the process of bug fixing, a temporal sequence of activities is done. Each activity is represented by a term. Useful semantic information and longterm dependency are available between terms in the sequence, but it is usually underutilised by existing bug fixing time predictor approaches. This work presents a novel deep learning-based model (called DeepLSTMPred) that (i) converts constituent terms to a vector of real numbers by considering their semantic meaning, (ii) finds the long-term dependencies between terms by deep long short term memory (LSTM) and (iii) classifies sequences to short fixing time or long fixing time. DeepLSTMPred is evaluated on bug reports extracted from the Mozilla project. The results show that the proposed method has better performance in comparison with a state-of-the-art approach (that is the hidden Markov-based model). The experimental results show that DeepLSTMPred achieves 15-20% improvement in terms of accuracy, precision, f-score, and recall.

show abstract

“…Word2vec is the common vector-based methods, in which words are mapped into vectors and similarity is the distance between two corresponding vectors [22]. As deep learning techniques has so excellent performance in natural language processing and computer vision [23], researchers has begun to apply it to software engineering, such as programming analysis [24], code plagiarism [25], code clone [26], code abstract generation, fault location and other applications [27,28]. These new deep learning approaches use representation learning to extract automatically useful information from the amount of unlabeled code data.…”

Section: Source Code Similaritymentioning

confidence: 99%

A Source Code Similarity Based on Siamese Neural Network

et al. 2020

View full text Add to dashboard Cite

Finding similar code snippets is a fundamental task in the field of software engineering. Several approaches have been proposed for this task by using statistical language model which focuses on syntax and structure of codes rather than deep semantic information underlying codes. In this paper, a Siamese Neural Network is proposed that maps codes into continuous space vectors and try to capture their semantic meaning. Firstly, an unsupervised pre-trained method that models code snippets as a weighted series of word vectors. The weights of the series are fitted by the Term Frequency-Inverse Document Frequency (TF-IDF). Then, a Siamese Neural Network trained model is constructed to learn semantic vector representation of code snippets. Finally, the cosine similarity is provided to measure the similarity score between pairs of code snippets. Moreover, we have implemented our approach on a dataset of functionally similar code. The experimental results show that our method improves some performance over single word embedding method.

show abstract

Deep Transfer Bug Localization

Cited by 60 publications

References 34 publications

Fast Changeset-based Bug Localization with BERT

Fast Changeset-based Bug Localization with BERT

Predicting the bug fixing time using word embedding and deep long short term memories

A Source Code Similarity Based on Siamese Neural Network

Contact Info

Product

Resources

About