Source code summaries give developers and maintainers vital information about source code methods. These summaries aid with the security of software systems as they can be used to improve developer and maintainer understanding of code, with the aim of reducing the number of bugs and vulnerabilities. However writing these summaries takes up the developers’ time and these summaries are often missing, incomplete, or outdated. Neural source code summarisation solves these issues by summarising source code automatically. Current solutions use Transformer neural networks to achieve this. We present CodeSumBART - a BART-base model for neural source code summarisation, pretrained on a dataset of Java source code methods and English method summaries. We present a new approach to training Transformers for neural source code summarisation by using epoch validation results to optimise the performance of the model. We found that in our approach, using larger n-gram precision BLEU metrics for epoch validation, such as BLEU-4, produces better performing models than other common NLG metrics.

Source code summaries are a vital tool for the understanding and maintenance of source code as they can be used to explain code in simple terms. However, source code with missing, incorrect, or outdated summaries is a common occurrence in production code. Automatic source code summarisation seeks to solve these issues by generating up-to-date summaries of source code methods. Recent work in automatically generating source code summaries uses neural networks for generating summaries; commonly Sequence-to-Sequence or Transformer models, pretrained on method-summary pairs. The most common method of evaluating the quality of these summaries is comparing the machine-generated summaries against human-written summaries. Summaries can be evaluated using n-gram-based translation metrics such as BLEU, METEOR, or ROUGE-L. However, these metrics alone can be unreliable and new Natural Language Generation metrics based on large pretrained language models provide an alternative. In this paper, we propose a method of improving the evaluation of a model by improving the preprocessing of the data used to train it, as well as proposing evaluating the model with a metric based off a language model, pretrained on a Natural Language (English) alongside traditional metrics. Our evaluation suggests our model has been improved by cleaning and preprocessing the data used in model training. The addition of a pretrained language model metric alongside traditional metrics shows that both produce results which can be used to evaluate neural source code summarisation.