Code Completion using Neural Attention and Byte Pair Encoding

Autor:	Arkesteijn, Youri, Saldanha, Nikhil, Kostense, Bastijn
Rok vydání:	2020
Předmět:	Computer Science - Computation and Language Computer Science - Machine Learning Computer Science - Software Engineering
Druh dokumentu:	Working Paper
Popis:	In this paper, we aim to do code completion based on implementing a Neural Network from Li et. al.. Our contribution is that we use an encoding that is in-between character and word encoding called Byte Pair Encoding (BPE). We use this on the source code files treating them as natural text without first going through the abstract syntax tree (AST). We have implemented two models: an attention-enhanced LSTM and a pointer network, where the pointer network was originally introduced to solve out of vocabulary problems. We are interested to see if BPE can replace the need for the pointer network for code completion. Comment: 4 pages, 4 figures, 1 table
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.06343 Zobrazit plný text záznamu View this record from Arxiv