Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach

Xie, Rui; Ye, Wei; Sun, Jinan; Zhang, Shikun

doi:10.1109/icpc52881.2021.00022

Cited by 18 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method name, which is present in every method, can be seen as an extremely concise summary of the method. Xie et al [57] analyze the method name and code summary in a Java dataset built by Leclair and McMillan [31], and find that on average 50.6% of the words in method names appear in the corresponding summaries, and 21.3% of the words in the summaries appear in the corresponding method names. For about 20% of the methods, all the words in the method names appear in the corresponding summaries.…”

Section: Methods Name Generationmentioning

confidence: 99%

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

Niu¹,

Li²,

Ng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent years have seen the successful application of large pretrained models to code representation learning, resulting in substantial improvements on many code-related downstream tasks. But there are issues surrounding their application to SE tasks. First, the majority of the pre-trained models focus on pre-training only the encoder of the Transformer. For generation tasks that are addressed using models with the encoder-decoder architecture, however, there is no reason why the decoder should be left out during pre-training. Second, many existing pre-trained models, including state-of-the-art models such as T5-learning, simply reuse the pretraining tasks designed for natural languages. Moreover, to learn the natural language description of source code needed eventually for code-related tasks such as code summarization, existing pretraining tasks require a bilingual corpus composed of source code and the associated natural language description, which severely limits the amount of data for pre-training. To this end, we propose SPT-Code, a sequence-to-sequence pre-trained model for source code. In order to pre-train SPT-Code in a sequence-to-sequence manner and address the aforementioned weaknesses associated with existing pre-training tasks, we introduce three pre-training tasks that are specifically designed to enable SPT-Code to learn knowledge of source code, the corresponding code structure, as well as a natural language description of the code without relying on any bilingual corpus, and eventually exploit these three sources of information when it is applied to downstream tasks. Experimental

show abstract

Section: Methods Name Generationmentioning

confidence: 99%

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

Niu¹,

Li²,

Ng³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, Neural Machine Translation (NMT) based models have been exploited to generate summaries for code snippets. CodeNN [19] is an early attempt that uses only code token sequences, followed by various approaches that utilize AST [2,15,16,21,22,25], API knowledge [17], type information [4], global context [13,25], reinforcement learning [42,43], multitask and dual learning [44,48,50], and pretrained language models [8].…”

Section: Comment Generationmentioning

confidence: 99%

HatCUP: Hybrid Analysis and Attention based Just-In-Time Comment Updating

Zhu,

He,

2022

Preprint

View full text Add to dashboard Cite

When changing code, developers sometimes neglect updating the related comments, bringing inconsistent or outdated comments. These comments increase the cost of program understanding and greatly reduce software maintainability. Researchers have put forward some solutions, such as CUP and HEBCUP, which update comments efficiently for simple code changes (i.e. modifying of a single token), but not good enough for complex ones. In this paper, we propose an approach named HatCUP (Hybrid Analysis and Attention based Comment UPdater), to provide a new mechanism for comment updating task. HatCUP pays attention to hybrid analysis and information. First, HatCUP considers the code structure change information and introduces a structure-guided attention mechanism combined with code change graph analysis and optimistic data flow dependency analysis. With a generally popular RNN-based encoder-decoder architecture, HatCUP takes the action of the code edits, the syntax, semantics and structure code changes, and old comments as inputs and generates a structural representation of the changes in the current code snippet. Furthermore, instead of directly generating new comments, HatCUP proposes a new edit or non-edit mechanism to mimic human editing behavior, by generating a sequence of edit actions and constructing a modified RNN model to integrate newly developed components. Evaluation on a popular dataset demonstrates that HatCUP outperforms the state-of-the-art deep learning-based approaches (CUP) by 53.8% for accuracy, 31.3% for recall and 14.3% for METEOR of the original metrics. Compared with the heuristic-based approach (HEBCUP), HatCUP also shows better overall performance. CCS CONCEPTS• Software and its engineering → Software maintenance tools; Maintaining software; Software evolution.

show abstract

“…Yao et al [353] and Ye et al [355] used StaQC dataset [354]; it contains more than 119 thousand pairs of question title and code snippet related to sql mined from StackOverflow. Xie et al [345] utilized two existing datasets-one each for Java [176] and Python [42]. Bansal et al [40] evaluated their code summarization technique using a Java dataset of 2.1M Java methods from 28K projects created by LeClair and McMillan [176].…”

Section: Data Collection and Processingmentioning

confidence: 99%

“…Yang et al [352] developed a multi-modal transformer-based code summarization approach for smart contracts. Xie et al [345] designed a novel multi-task learning (mlt) approach for code summarization through mining the relationship between method-code summaries and method names. Bansal et al [40] introduced a project-level encoder dl model for code summarization.…”

Section: Model Trainingmentioning

confidence: 99%

A Survey on Machine Learning Techniques for Source Code Analysis

Sharma¹,

Kechagia²,

Georgiou³

et al. 2021

Preprint

View full text Add to dashboard Cite

Context:The advancements in machine learning techniques have encouraged researchers to apply these techniques to a myriad of software engineering tasks that use source code analysis such as testing and vulnerabilities detection. A large number of studies poses challenges to the community to understand the current landscape. Objective: We aim to summarize the current knowledge in the area of applied machine learning for source code analysis. Method: We investigate studies belonging to twelve categories of software engineering tasks and corresponding machine learning techniques, tools, and datasets that have been applied to solve them. To do so, we carried out an extensive literature search and identified 364 primary studies published between 2002 and 2021. We summarize our observations and findings with the help of the identified studies. Results: Our findings suggest that the usage of machine learning techniques for source code analysis tasks is consistently increasing. We synthesize commonly used steps and the overall workflow for each task, and summarize the employed machine learning techniques. Additionally, we collate a comprehensive list of available datasets and tools useable in this context. Finally, we summarize the perceived challenges in this area that include availability of standard datasets, reproducibility and replicability, and hardware resources. CCS Concepts: • Software and its engineering → Software libraries and repositories; Software maintenance tools; Software post-development issues; Maintaining software; • Computing methodologies → Machine learning.

show abstract

Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach

Cited by 18 publications

References 21 publications

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

HatCUP: Hybrid Analysis and Attention based Just-In-Time Comment Updating

A Survey on Machine Learning Techniques for Source Code Analysis

Contact Info

Product

Resources

About