%0 Conference Proceedings
%T Exploring Dynamic Selection of Branch Expansion Orders for Code Generation
%A Jiang, Hui
%A Zhou, Chulun
%A Meng, Fandong
%A Zhang, Biao
%A Zhou, Jie
%A Huang, Degen
%A Wu, Qingqiang
%A Su, Jinsong
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F jiang-etal-2021-exploring
%X Due to the great potential in facilitating software development, code generation has attracted increasing attention recently. Generally, dominant models are Seq2Tree models, which convert the input natural language description into a sequence of tree-construction actions corresponding to the pre-order traversal of an Abstract Syntax Tree (AST). However, such a traversal order may not be suitable for handling all multi-branch nodes. In this paper, we propose to equip the Seq2Tree model with a context-based Branch Selector, which is able to dynamically determine optimal expansion orders of branches for multi-branch nodes. Particularly, since the selection of expansion orders is a non-differentiable multi-step operation, we optimize the selector through reinforcement learning, and formulate the reward function as the difference of model losses obtained through different expansion orders. Experimental results and in-depth analysis on several commonly-used datasets demonstrate the effectiveness and generality of our approach. We have released our code at https://github.com/DeepLearnXMU/CG-RL.
%R 10.18653/v1/2021.acl-long.394
%U https://aclanthology.org/2021.acl-long.394
%U https://doi.org/10.18653/v1/2021.acl-long.394
%P 5076-5085