Source Code Summarization

37 papers with code • 9 benchmarks • 7 datasets

Code Summarization is a task that tries to comprehend code and automatically generate descriptions directly from the source code.

Source: Improving Automatic Source Code Summarization via Deep Reinforcement Learning

Libraries

Use these libraries to find Source Code Summarization models and implementations
2 papers
21

A Prompt Learning Framework for Source Code Summarization

wssun/promptcs 26 Dec 2023

PromptCS trains a prompt agent that can generate continuous prompts to unleash the potential for LLMs in code summarization.

2
26 Dec 2023

Revisiting File Context for Source Code Summarization

apcl-research/transformerfc 5 Sep 2023

Source code summarization is the task of writing natural language descriptions of source code.

0
05 Sep 2023

Distilled GPT for Source Code Summarization

apcl-research/jam-cgpt 28 Aug 2023

A code summary is a brief natural language description of source code.

2
28 Aug 2023

Semantic Similarity Loss for Neural Source Code Summarization

apcl-research/funcom-useloss 14 Aug 2023

We also propose to combine our loss with traditional CCE for each word, which streamlines the training process compared to baselines.

2
14 Aug 2023

Statement-based Memory for Neural Source Code Summarization

aakashba/smncode2022 21 Jul 2023

For example, by taking the entire subroutine as input to a Transformer or RNN-based encoder.

1
21 Jul 2023

Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization

tongye98/sourcecodesummary 18 May 2023

In this paper, we propose a fine-grained Token-level retrieval-augmented mechanism (Tram) on the decoder side rather than the encoder side to enhance the performance of neural models and produce more low-frequency tokens in generating summaries.

1
18 May 2023

An Extractive-and-Abstractive Framework for Source Code Summarization

wssun/eacs 15 Jun 2022

The extractive module in the framework performs a task of extractive code summarization, which takes in the code snippet and predicts important statements containing key factual details.

4
15 Jun 2022

M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for Source Code Summarization

transms/m2ts 18 Mar 2022

They use the learned code representations as input to code summarization models, which can accordingly generate summaries describing source code.

21
18 Mar 2022

Source Code Summarization with Structural Relative Position Guided Transformer

gonez5/script 14 Feb 2022

We further show that how the proposed SCRIPT captures the structural relative dependencies.

18
14 Feb 2022

Compositionality-Aware Graph2Seq Learning

itakeshi/mlap-graph2seq 28 Jan 2022

It is expected that the compositionality in a graph can be associated to the compositionality in the output sequence in many graph2seq tasks.

3
28 Jan 2022