Evaluating Code Comment Generation With Summarized API Docs

TL;DR: This paper proposes to evaluate how summarizing the API Docs using an extractive text summarization technique, TextRank, will impact the overall performance of the API2Com, and confirms the inverse correlation between the number of APIs and the model's performance.

Abstract: Code comment generation is the task of generating a high-level natural language description for a given code snippet. API2Com is a comment generation model designed to leverage the Application Programming Interface Documentations (API Docs) as an external knowledge resource. Shahbazi et al. [1] showed that API Docs might help increase the model's performance. However, the model's performance in generating pertinent comments deteriorates due to the lengthy documentation used in the input as the number of APIs used in a method increases. In this paper, we propose to evaluate how summarizing the API Docs using an extractive text summarization technique, TextRank, will impact the overall performance of the API2Com. The results of our experiments using the same Java dataset confirm the inverse correlation between the number of APIs and the model's performance. As the number of APIs increases, the performance metrics tend to deteriorate for both configurations of the model, with or without API Docs summarization using TextRank. Experiments also show the impact of the number of APIs on TextRank algorithm capacity to improve the model per-formance. For example, with 8 APIs, TextRank summarization improved the model BLEU score by 18% on average, but the performance tends to decrease as the number of APIs increases. This demonstrates an open area of research to determine the winning combination in terms of the model configuration and the length of documentation used.