An AST Structure Enhanced Decoder for Code Generation

doi:10.1109/TASLP.2021.3138717

An AST Structure Enhanced Decoder for Code Generation

2022-01-01

7

PRE

AI

DOI：10.1109/TASLP.2021.3138717

Original

Original request for help

Save

Abstract

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)

Keywords:

Codes

Decoding

Syntactics

Predictive models

History

Grammar

Speech processing

Code generation

abstract syntax tree

attention mechanism

future action prediction

An AST Structure Enhanced Decoder for Code Generation

Abstract

Journal

Organization