30 июл. 2024 г. · A Transformer-based Approach for Source Code Summarization. Official implementation of our ACL 2020 paper on Source Code Summarization.

To learn code representation for summarization, we explore the Transformer model that uses a self-attention mechanism and has shown to be effective in capturing ...

1 мая 2020 г. · We explore the Transformer model that uses a self-attention mechanism and has shown to be effective in capturing long-range dependencies.

We propose to use Transformer (Vaswani et al.,. 2017) to generate a natural language summary given a piece of source code. Both the code and summary is a ...

In this article, we propose a novel approach named SG-Trans to incorporate code structural properties into Transformer.

14 февр. 2022 г. · Abstract:Source code summarization aims at generating concise and clear natural language descriptions for programming languages.

Transformer-based approaches for an efficient docstrings generation on a piece of Python's code. - martysai/source-code-summarization.

Improving automatic source code summarization via deep reinforcement learning. ASE 2018. 10. Page 11. Positional Encoding (PE) of Code Tokens.

Code summarization (CS) is becoming a promising area in recent language understanding, which aims to generate sensible human language automatically for ...

In this paper, we provide a novel way to generate code summaries by combining a graph-based neural network and a Transformer-XL network.