On the evaluation of neural code summarization
… are from solving this problem and provide suggestions to future research, in this paper, we
… code summarization models more correctly and comprehensively, we need to pay much …
… code summarization models more correctly and comprehensively, we need to pay much …
Improved code summarization via a graph neural network
… chose not to include Hu et al. in our baselines because the work done by LeClair et al.
built upon their work and was shows to have higher performance, and is much closer to our …
built upon their work and was shows to have higher performance, and is much closer to our …
Retrieval-based neural source code summarization
… set and the online code retrieval during testing, our approach may cost much more time to
… However, we only need 89 ms in average to generate the summary for each testing code …
… However, we only need 89 ms in average to generate the summary for each testing code …
Semantic similarity loss for neural source code summarization
CY Su, C McMillan - Journal of Software: Evolution and …, 2023 - Wiley Online Library
… We present our evaluation in two experiments. First, we train different neural code summarization
… CCE loss, as we established in Section 2, is by far the main means of computing loss …
… CCE loss, as we established in Section 2, is by far the main means of computing loss …
Towards retrieval-based neural code summarization: A meta-learning approach
Z Zhou, H Yu, G Fan, Z Huang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
… , we propose a brand-new framework for code summarization based on meta-learning and
code … As far as we know, the offline training dataset for the neural model is always used as …
code … As far as we know, the offline training dataset for the neural model is always used as …
Semantic similarity metrics for evaluating source code summarization
… By far the most popular metric for measuring word overlap in source … Second, a vast
majority of neural code summarization approaches are based on this, or a similar variant of this …
majority of neural code summarization approaches are based on this, or a similar variant of this …
A human study of comprehension and code summarization
… summary using state-of-the-art neural summarization. The intended purpose of the … are
not reliable predictors of how much a summary helps them understand code. This aligns with …
not reliable predictors of how much a summary helps them understand code. This aligns with …
Why my code summarization model does not work: Code comment improvement with category prediction
… 6.9, which is much lower than the standard deviation of tokens of codes. Considering that …
models (eg, CodeNN is the first to apply a neural network to code summarization), or they are …
models (eg, CodeNN is the first to apply a neural network to code summarization), or they are …
Project-level encoding for neural source code summarization of subroutines
… We then use a fully-connected layer to squash these long vectors back to the specified vector
… We use four baseline neural code summarization techniques. We then augment each with …
… We use four baseline neural code summarization techniques. We then augment each with …
Do Code Summarization Models Process Too Much Information? Function Signature May Be All That Is Needed
… , we observe that code summarization models can be easily overloaded with source code.
A … [53] conduct a comprehensive analysis of ive state-of-the-art neural code summarization …
A … [53] conduct a comprehensive analysis of ive state-of-the-art neural code summarization …