返回
An AST Structure Enhanced Decoder for Code Generation
DOI:10.1109/TASLP.2021.3138717.png)
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
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Evaluation of awareness about pharmacovigilance and adverse drug reaction monitoring in resident doctors of a tertiary care teaching hospital对三级护理教学医院住院医师关于药物警戒和不良反应监测的认知评估
Deep Illumina-Based Shotgun Sequencing Reveals Dietary Effects on the Structure and Function of the Fecal Microbiome of Growing Kittens
PLoS ONE
IF0
Perception of pharmacovigilance among doctors in a tertiary care hospital: Influence of an interventional lecture三级医院医生对药物警戒的认知:干预性讲座的影响

