Meta Learning for Code Summarization
This work addresses code summarization for developers by improving accuracy through model combination, but it is incremental as it builds on existing models.
The paper tackled the problem of source code summarization by showing that three state-of-the-art models perform well on disjoint subsets of a code-base, and proposed meta-models to combine them, resulting in a 2.1 BLEU point improvement over the best individual model.
Source code summarization is the task of generating a high-level natural language description for a segment of programming language code. Current neural models for the task differ in their architecture and the aspects of code they consider. In this paper, we show that three SOTA models for code summarization work well on largely disjoint subsets of a large code-base. This complementarity motivates model combination: We propose three meta-models that select the best candidate summary for a given code segment. The two neural models improve significantly over the performance of the best individual model, obtaining an improvement of 2.1 BLEU points on a dataset of code segments where at least one of the individual models obtains a non-zero BLEU.