Saved in:
Bibliographic Details
Main Authors: Martins, Marcelo de Rezende, Gerosa, Marco A.
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2009.01959
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917572337729536
author Martins, Marcelo de Rezende
Gerosa, Marco A.
author_facet Martins, Marcelo de Rezende
Gerosa, Marco A.
contents Software developers routinely search for code using general-purpose search engines. However, these search engines cannot find code semantically unless it has an accompanying description. We propose a technique for semantic code search: A Convolutional Neural Network approach to code retrieval (CoNCRA). Our technique aims to find the code snippet that most closely matches the developer's intent, expressed in natural language. We evaluated our approach's efficacy on a dataset composed of questions and code snippets collected from Stack Overflow. Our preliminary results showed that our technique, which prioritizes local interactions (words nearby), improved the state-of-the-art (SOTA) by 5% on average, retrieving the most relevant code snippets in the top 3 (three) positions by almost 80% of the time. Therefore, our technique is promising and can improve the efficacy of semantic code retrieval.
format Preprint
id arxiv_https___arxiv_org_abs_2009_01959
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle CoNCRA: A Convolutional Neural Network Code Retrieval Approach
Martins, Marcelo de Rezende
Gerosa, Marco A.
Machine Learning
Computation and Language
Software Engineering
Software developers routinely search for code using general-purpose search engines. However, these search engines cannot find code semantically unless it has an accompanying description. We propose a technique for semantic code search: A Convolutional Neural Network approach to code retrieval (CoNCRA). Our technique aims to find the code snippet that most closely matches the developer's intent, expressed in natural language. We evaluated our approach's efficacy on a dataset composed of questions and code snippets collected from Stack Overflow. Our preliminary results showed that our technique, which prioritizes local interactions (words nearby), improved the state-of-the-art (SOTA) by 5% on average, retrieving the most relevant code snippets in the top 3 (three) positions by almost 80% of the time. Therefore, our technique is promising and can improve the efficacy of semantic code retrieval.
title CoNCRA: A Convolutional Neural Network Code Retrieval Approach
topic Machine Learning
Computation and Language
Software Engineering
url https://arxiv.org/abs/2009.01959