Page 159 - 《软件学报》2021年第5期

顾斌 等:程序智能合成技术研究进展 1383

[18] Yin P, Neubig G. A syntactic neural model for general-purpose code generation. In: Proc. of the 55th Annual Meeting of the
Association for Computational Linguistics, Vol.1. 2017. 440−450. [doi: 10.18653/v1/P17-1041].
[19] Beltagy I, Quirk C. Improved semantic parsers for if-then statements. In: Proc. of the 54th Annual Meeting of the Association for
Computational Linguistics, Vol.1. 2016. 726−736.
[20] Cai R, Xu B, Yang X, et al. An encoder-decoder framework translating natural language to database queries. arXiv preprint arXiv:
1711.06061, 2017.
[21] Alur R, Martin M, Raghothaman M, et al. Synthesizing finite-state protocols from scenarios and requirements. In: Proc. of the 10th
Int’l Haifa Verification Conf. (HVC). 2014. 75−91.
[22] Hughes J, Sparks C, Stoughton A, et al. Building resource adaptive software systems (BRASS): Objectives and system evaluation.
ACM SIGSOFT Software Engineering Notes, 2016,41(1):1−2.
[23] Intent-defined adaptive software (IDAS). Broad Agency Announcement, 2019. https://www.darpa.mil/program/
[24] Shaw D, Wart W, Green C. Inferring LISP programs from examples. In: Proc. of the 4th Int’1 Joint Conf. on Artificial Intelligence
(IJCAI), Vol.1. 1975. 260−267.
[25] Summers PD. A methodology for LISP program construction from examples. Journal of the ACM, 1977,24(1):161−175.
[26] Manna Z, Waldinger R. Synthesis: Dreams→programs. IEEE Trans. on Software Engineering, 1979,5(4):294−328.
[27] Manna Z, Waldinger R. A deductive approach to program synthesis. ACM Trans. on Programming Languages and Systems
(TOPLAS), 1980,2(1):90−121.
[28] Kitzelmann E. Analytical inductive functional programming. In: Proc. of the 18th Int’1 Symp. on Logic-based Program Synthesis
and Transformation (LOPSTR). 2009. 87−102.
[29] Bornholt J, Torlak E. Scaling program synthesis by exploiting existing code. In: Proc. of the Machine Learning for Programming
Languages Workshop (ML4PL). 2015.
[30] Reed S, De Freitas N. Neural programmer-interpreters. In: Proc. of the Int’l Conf. on Learning Representations (ICLR). 2016.
[31] Li CT, Tarlow D, et al. Neural program lattices. In: Proc. of the Int’l Conf. on Learning Representations (ICLR). 2017.
[32] Cai J, Shin R, Song D. Making neural programming architectures generalize via recursion. In: Proc. of the Int’l Conf. on Learning
Representations (ICLR). 2017.
[33] Devlin J, Uesato J, Bhupatiraju S, et al. RobustFill: Neural program learning under noisy I/O. In: Proc. of the 34th Int’l Conf. on
Machine Learning. 2017. 990−998.
[34] Guo Z, James M, Justo D, et al. Program Synthesis by Type-guided Abstraction Refinement. In: Proc. of the ACM on Programming
Languages 4 (POPL). 2019. 1−28.
[35] Balog M, Gaunt AL, Brockschmidt M, et al. Deepcoder: Learning to write programs. arXiv preprint arXiv:1611.01989, 2016.
[36] Becker K, Gottschlich J. AI programmer: Autonomously creating software programs using genetic algorithms. arXiv preprint arXiv:
1709.05703, 2017.
[37] Parisotto E, Mohamed A, Singh R, et al. Neuro-symbolic program synthesis. arXiv preprint arXiv:1611.01855, 2016.
[38] Solar-Lezama A. Program synthesis by sketching [Ph.D. Thesis]. Berkeley: University of California, 2008.
[39] Alur R, Černý P, Madhusudan P, et al. Synthesis of interface specifications for Java classes. In: Proc. of the 32nd ACM SIGPLAN-
SIGACT Symp. on Principles of Programming Languages (POPL). ACM, 2005. 98−109.
[40] Murali V, Qi L, Chaudhuri S, et al. Neural sketch learning for conditional program generation. arXiv preprint arXiv:1703.05698,
2017.
[41] Alur R, Bodik R, Juniwal G, et al. Syntax-guided synthesis. In: Proc. of the Formal Methods in Computer-aided Design. IEEE,
2013.
[42] Alur R, Singh R, Fisman D, et al. Search-based program synthesis. Communications of the ACM, 2018,61(12):84−93.
[43] Yaghmazadeh N, Wang YP, Dillig I, et al. Type- and content-driven synthesis of SQL queries from natural language. arXiv
preprint arXiv:1702.01168, 2017.
[44] Luan S, Yang D, Barnaby C, et al. Aroma: Code recommendation via structural code search. arXiv preprint arXiv:1812.01158,
2018.
[45] Chi C, Xin P, Jun S, et al. Generative API usage code recommendation with parameter concretization. Science China Information
Sciences, 2019,62(9):51−72.
[46] Hu X, Men R, Li G, et al. Deep-AutoCoder: Learning to complete code precisely with induced code tokens. In: Proc. of the 43rd
Annual Computer Software and Applications Conf. (COMPSAC). IEEE, 2019. 159−168.