arrow
返回

An AST Structure Enhanced Decoder for Code Generation

delete2022-01-01
delete7
PRE
AI
H
Hui Jiang
L
Linfeng Song
Y
Yubin Ge
F
Fandong Meng
姚俊峰 封面图
姚俊峰 (Junfeng Yao)
J
Jinsong Su *
DOI:10.1109/TASLP.2021.3138717delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Currently, the most dominant neural code generation modelsare often equipped with a tree-structured LSTM decoder, which outputs a sequence of actions to construct an Abstract Syntax Tree (AST) via pre-order traversal. However, such a decoder has two obvious drawbacks. First, except for the parent action, other faraway and important history actions rarely contribute to the current decision. Second, it also neglects future actions, which may be crucial for the prediction of the current action. To deal with these issues, in this paper, we propose a novel AST structure enhanced decoder for code generation, which significantly extends the decoder with respect to the above two aspects. First, we introduce an AST information enhanced attention mechanism to fully exploit history actions, of which impacts are further distinguished according to their syntactic distances, action types and relative positions; Second, we jointly model the predictions of current action and its important future action via multi-task learning, where the learned hidden state of the latter can be further leveraged to improve the former. Experimental results on commonly-used datasets demonstrate the effectiveness of our proposed decoder.(1)
Keyword:
Codes
Decoding
Syntactics
Predictive models
History
Grammar
Speech processing
Code generation
abstract syntax tree
attention mechanism
future action prediction

期刊

I
IEEE-ACM Transactions on Audio Speech and Language Processing
IF:
5.1
论文数:
2.6K
被引数:
1.1W

机构

U
University of Illinois Urbana-Champaign
学者数:
2.4W
论文数: 2.0W
被引数: 35
University of Illinois System 封面图
University of Illinois System
学者数:
6.9W
论文数: 6.2W
被引数: 644
X
xiamen university
学者数:
5.9W
论文数: 3.8W
被引数: 67
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
Exploiting reverse target-side contexts for neural machine translation via asynchronous bidirectional decoding
err2019-12-01
err27
errOAAI
errSu, Jinsong; Zhang, Xiangwen; Lin, Qian; Qin, Yue; Yao, Junfeng; Liu, Yang
err分享
err收藏
Deep Illumina-Based Shotgun Sequencing Reveals Dietary Effects on the Structure and Function of the Fecal Microbiome of Growing Kittens
err2014-07-10
err0
errOAAI
errOliver Deusch; Ciaran O’Flynn; Alison Colyer; Penelope Morris; David Allaway; Paul G. Jones; Kelly S. Swanson
err分享
err收藏
Pattern Transformation Triggered by Deformation
err2007-08-22
err0
PREAI
errT. Mullin; S. Deschanel; K. Bertoldi; M. C. Boyce
err分享
err收藏
学者 查看更多内容