# Meta Learning for Code Summarization

arXiv: https://arxiv.org/abs/2201.08310 · HTML: https://mlsanity.com/paper/2201.08310/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 20 Jan 2022.

## Builds on (most cited first, 12 of 12)

- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [A Transformer-based Approach for Source Code Summarization](https://mlsanity.com/paper/2005.00653/) (2020)
- [Improving Automatic Source Code Summarization via Deep Reinforcement Learning](https://mlsanity.com/paper/1811.07234/) (2018)
- [Improved Code Summarization via a Graph Neural Network](https://mlsanity.com/paper/2004.02843/) (2020)
- [A Neural Model for Generating Natural Language Summaries of Program Subroutines](https://mlsanity.com/paper/1902.01954/) (2019)
- [Code Generation as a Dual Task of Code Summarization](https://mlsanity.com/paper/1910.05923/) (2019)
- [Recommendations for Datasets for Source Code Summarization](https://mlsanity.com/paper/1904.02660/) (2019)
- [Improved Automatic Summarization of Subroutines via Attention to File Context](https://mlsanity.com/paper/2004.04881/) (2020)
- [Project-Level Encoding for Neural Source Code Summarization of Subroutines](https://mlsanity.com/paper/2103.11599/) (2021)
- [Dissecting Span Identification Tasks with Performance Prediction](https://mlsanity.com/paper/2010.02587/) (2020)
- [Ensemble Models for Neural Source Code Summarization of Subroutines](https://mlsanity.com/paper/2107.11423/) (2021)
- [Automatically Extracting Subroutine Summary Descriptions from Unstructured Comments](https://mlsanity.com/paper/1912.10198/) (2019)

## Abstract (arXiv)

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.