A Convolutional Attention Network for Extreme Summarization of Source\n Code
Abstract
Attention mechanisms in neural networks have proved useful for problems in\nwhich the input and output do not have fixed dimension. Often there exist\nfeatures that are locally translation invariant and would be valuable for\ndirecting the model's attention, but previous attentional architectures are not\nconstructed to learn such features specifically. We introduce an attentional\nneural network that employs convolution on the input tokens to detect local\ntime-invariant and long-range topical attention features in a context-dependent\nway. We apply this architecture to the problem of extreme summarization of\nsource code snippets into short, descriptive function name-like summaries.\nUsing those features, the model sequentially generates a summary by\nmarginalizing over two attention mechanisms: one that predicts the next summary\ntoken based on the attention weights of the input tokens and another that is\nable to copy a code token as-is directly into the summary. We demonstrate our\nconvolutional attention neural network's performance on 10 popular Java\nprojects showing that it achieves better performance compared to previous\nattentional mechanisms.\n
Read the paper
Related studies
- Regulation of nucleolus assembly by non-coding RNA polymerase II transcripts
- For a Healthy Histone Code, a Little SUMO in the Tail Keeps the Acetyl Away
- Discovering a binary CTCF code with a little help from BORIS
- Article Commentary: Stabilizing the Code–-Methods to Preserve RNA Prove Their Worth
- Foreword to the Special Issue for the RINTC (The Implicit Seismic Risk of Code-Conforming Structures) Project
- Commentary: Promoting Health and Well-being in Pediatric Primary Care Settings: Using Health and Behavior Codes at Routine Well-child Visits
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.