Improved Code Summarization via a Graph Neural Network

LeClair, Alexander; Haque, Sakib; Wu, Lingfei; McMillan, Collin

doi:10.1145/3387904.3389268

Cited by 242 publications

(163 citation statements)

References 31 publications

Supporting

Mentioning

153

Contrasting

Order By: Relevance

“…Alon et al (2019) represented source code based on AST paths between pairs of tokens. LeClair et al (2020) proposed a model that encoded the AST of source code using graph neural networks. These approaches utilized ASTs to capture structural features, but less considered the sequence characteristics of code in a program language.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning Sequential and Structural Information for Source Code Summarization

Choi¹,

Bak²,

Na³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

We propose a model that learns both the sequential and the structural features of code for source code summarization. We adopt the abstract syntax tree (AST) and graph convolution to model the structural information and the Transformer to model the sequential information. We convert code snippets into ASTs and apply graph convolution to obtain structurally-encoded node representations. Then, the sequences of the graphconvolutioned AST nodes are processed by the Transformer layers. Since structurallyneighboring nodes will have similar representations in graph-convolutioned trees, the Transformer layers can effectively capture not only the sequential information but also the structural information such as sentences or blocks of source code. We show that our model outperforms the state-of-the-art for source code summarization by experiments and human evaluations.

show abstract

Section: Related Workmentioning

confidence: 99%

“…On the other hand, Shido et al (2019); Harer et al (2019); LeClair et al (2020); Scarselli et al (2008) proposed tree-based models to capture the features of the source code. They used the structural information from parse trees but hardly considered the sequence information of code tokens.…”

Section: Introductionmentioning

confidence: 99%

Learning Sequential and Structural Information for Source Code Summarization

Choi¹,

Bak²,

Na³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

show abstract

“…LeClair et al (2019) proposes to use both AST sequences and source code sequence as multiple input for model. LeClair et al (2020) proposes to employ GNN over AST structures to better extract structure information. Our work, on the contrast, explores broader context, class-level neighboring functions, to introduce rich information for comment generation.…”

Section: Related Workmentioning

confidence: 99%

Towards Context-Aware Code Comment Generation

Huang

Wang

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Code comments are vital for software maintenance and comprehension, but many software projects suffer from the lack of meaningful and up-to-date comments in practice. This paper presents a novel approach to automatically generate code comments at a function level by targeting object-oriented programming languages. Unlike prior work that only uses information locally available within the target function, our approach leverages broader contextual information by considering all other functions of the same class. To propagate and integrate information beyond the scope of the target function, we design a novel learning framework based on the bidirectional gated recurrent unit and a graph attention network with a pointer mechanism. We apply our approach to produce code comments for Java methods and compare it against four strong baseline methods. Experimental results show that our approach outperforms most methods by a large margin and achieves a comparable result with the state-of-the-art method.

show abstract

“…Previous approaches could be divided into two categories. The first is to employ non-sequential encoders (e.g., TBCNN (Mou et al, 2016), Tree-LSTM (Shido et al, 2019), Tree-Transformer (Harer et al, 2019), Graph Neural Network (Allamanis et al, 2018;Alex et al, 2020;Wang et al, 2021)) to directly model structural inputs. The other is to pre-process structural inputs to apply sequential models on them.…”

Section: Introductionmentioning

confidence: 99%

Code Summarization with Structure-induced Transformer

Wu¹,

Zhao²,

Zhang³

2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Code summarization (CS) is becoming a promising area in recent language understanding, which aims to generate sensible human language automatically for programming language in the format of source code, serving in the most convenience of programmer developing. It is well known that programming languages are highly structured. Thus previous works attempt to apply structurebased traversal (SBT) or non-sequential models like Tree-LSTM and graph neural network (GNN) to learn structural program semantics. However, it is surprising that incorporating SBT into advanced encoder like Transformer instead of LSTM has been shown no performance gain, which lets GNN become the only rest means modeling such necessary structural clue in source code. To release such inconvenience, we propose structureinduced Transformer, which encodes sequential code inputs with multi-view structural clues in terms of a newly-proposed structureinduced self-attention mechanism. Extensive experiments show that our proposed structureinduced Transformer helps achieve new stateof-the-art results on benchmarks.

show abstract

Improved Code Summarization via a Graph Neural Network

Cited by 242 publications

References 31 publications

Learning Sequential and Structural Information for Source Code Summarization

Learning Sequential and Structural Information for Source Code Summarization

Towards Context-Aware Code Comment Generation

Code Summarization with Structure-induced Transformer

Contact Info

Product

Resources

About