A Transformer-based Approach for Source Code Summarization

wasiahmad/NeuralCodeSum • • ACL 2020

Generating a readable summary that describes the functionality of a program is known as source code summarization.

Recommendations for Datasets for Source Code Summarization

transms/m2ts • • NAACL 2019

The main use for these descriptions is in software documentation e. g. the one-sentence Java method descriptions in JavaDocs.

code2seq: Generating Sequences from Structured Representations of Code

tech-srl/code2seq • • ICLR 2019

The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval.

Structured Neural Summarization

CoderPat/structured-neural-summarization • • ICLR 2019

Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input.

Improving Automatic Source Code Summarization via Deep Reinforcement Learning

mf1832146/tree_transformer_2.0 • • 17 Nov 2018

To the best of our knowledge, most state-of-the-art approaches follow an encoder-decoder framework which encodes the code into a hidden space and then decode it into natural language space, suffering from two major drawbacks: a) Their encoders only consider the sequential content of code, ignoring the tree structure which is also critical for the task of code summarization, b) Their decoders are typically trained to predict the next word by maximizing the likelihood of next ground-truth word with previous ground-truth word given.

Code Generation as a Dual Task of Code Summarization

Bolin0215/CSCGDual • • NeurIPS 2019

Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development.

Improved Code Summarization via a Graph Neural Network

acleclair/ICPC2020_GNN • • 6 Apr 2020

The first approaches to use structural information flattened the AST into a sequence.

Unified Pre-training for Program Understanding and Generation

wasiahmad/PLBART • • NAACL 2021

Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models.

HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks

dakuo/haconvgnn • • Findings (EMNLP) 2021

Jupyter notebook allows data scientists to write machine learning code together with its documentation in cells.

Summarizing Source Code using a Neural Attention Model

sriniiyer/codenn • • ACL 2016