Code-to-Vector (code2vec) Neural Network: Difference between revisions

From GM-RKB
Jump to navigation Jump to search
m (Text replacement - "]] ** " to "]]. ** ")
m (Text replacement - ". " to ". ")
 
Line 1: Line 1:
A [[Code-to-Vector (code2vec) Neural Network]] is a [[Path-Attention Neural Network]] that uses a [[representation]] of arbitrary-sized [[code snippet]]s and learns to aggregate multiple [[syntactic path]]s into a single [[fixed-size vector]].  
A [[Code-to-Vector (code2vec) Neural Network]] is a [[Path-Attention Neural Network]] that uses a [[representation]] of arbitrary-sized [[code snippet]]s and learns to aggregate multiple [[syntactic path]]s into a single [[fixed-size vector]].
* <B>AKA:</B> [[Code-to-Vector (code2vec) Neural Network|Code2Vec]].
* <B>AKA:</B> [[Code-to-Vector (code2vec) Neural Network|Code2Vec]].
* <B>Context:</B>
* <B>Context:</B>
Line 18: Line 18:


=== 2019 ===
=== 2019 ===
* ([[2019_Code2vecLearningDistributedRepr|Alon et al., 2019]]) ⇒ [[author::Uri Alon]], [[Meital Zilberstein]], [[Omer Levy]], and [[Eran Yahav]]. ([[2019]]). &ldquo;[https://arxiv.org/pdf/1803.09473.pdf code2vec: Learning Distributed Representations of Code].&rdquo; In: [[Proceedings of the ACM on Programming Languages (POPL), Volume 3]].  
* ([[2019_Code2vecLearningDistributedRepr|Alon et al., 2019]]) ⇒ [[author::Uri Alon]], [[Meital Zilberstein]], [[Omer Levy]], and [[Eran Yahav]]. ([[2019]]). &ldquo;[https://arxiv.org/pdf/1803.09473.pdf code2vec: Learning Distributed Representations of Code].&rdquo; In: [[Proceedings of the ACM on Programming Languages (POPL), Volume 3]].
** QUOTE: The goal of this paper is to learn [[code embedding]]s, [[continuous vector]]s for representing [[snippets of code]]. By learning [[code embedding]]s, our long-term goal is to enable the [[application]] of [[neural technique]]s to a wide-range of [[programming-languages task]]s. In this paper, we use the motivating [[task of semantic labeling of code snippets]].
** QUOTE: The goal of this paper is to learn [[code embedding]]s, [[continuous vector]]s for representing [[snippets of code]]. By learning [[code embedding]]s, our long-term goal is to enable the [[application]] of [[neural technique]]s to a wide-range of [[programming-languages task]]s. In this paper, we use the motivating [[task of semantic labeling of code snippets]].



Latest revision as of 17:20, 1 August 2022