Neural Code CompletionDownload PDF

29 May 2024 (modified: 21 Jul 2022)Submitted to ICLR 2017Readers: Everyone
Abstract: Code completion, an essential part of modern software development, yet can bechallenging for dynamically typed programming languages. In this paper we ex-plore the use of neural network techniques to automatically learn code completionfrom a large corpus of dynamically typed JavaScript code. We show differentneural networks that leverage not only token level information but also structuralinformation, and evaluate their performance on different prediction tasks. Wedemonstrate that our models can outperform the state-of-the-art approach, whichis based on decision tree techniques, on both next non-terminal and next terminalprediction tasks by 3.8 points and 0.5 points respectively. We believe that neuralnetwork techniques can play a transformative role in helping software developersmanage the growing complexity of software systems, and we see this work as afirst step in that direction.
Conflicts: berkeley.edu
Keywords: Deep learning, Applications
18 Replies

Loading