Code to Comment Translation: A Comparative Study on Model Effectiveness & Errors
This work addresses the problem of evaluating code summarization models for software engineers by highlighting error modes, but it is incremental as it builds on existing models without introducing new methods.
The study compared three state-of-the-art models for automated source code summarization, finding that quantitative metrics like BLEU-4, METEOR, and ROUGE-L do not fully capture model errors, and it developed an error taxonomy through qualitative analysis to guide future research.
Automated source code summarization is a popular software engineering research topic wherein machine translation models are employed to "translate" code snippets into relevant natural language descriptions. Most evaluations of such models are conducted using automatic reference-based metrics. However, given the relatively large semantic gap between programming languages and natural language, we argue that this line of research would benefit from a qualitative investigation into the various error modes of current state-of-the-art models. Therefore, in this work, we perform both a quantitative and qualitative comparison of three recently proposed source code summarization models. In our quantitative evaluation, we compare the models based on the smoothed BLEU-4, METEOR, and ROUGE-L machine translation metrics, and in our qualitative evaluation, we perform a manual open-coding of the most common errors committed by the models when compared to ground truth captions. Our investigation reveals new insights into the relationship between metric-based performance and model prediction errors grounded in an empirically derived error taxonomy that can be used to drive future research efforts