Neural Sketch Learning for Conditional Program Generation

By Vijayaraghavan Murali, Letao Qi, Swarat Chaudhuri, C. Jermaine. 2017

141 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Prompting & Reasoning

Citations in the corpus

Competition-level code generation with AlphaCode (2022, methodology): “, 2016), generate program sketches (Guo et al., 2021; Murali et al., 2017), convert pseudocode to code (Kulal et al.”
Program Synthesis with Large Language Models (2021, methodology): “For example, BAYOU generates API-heavy code in Java using a latent-variable probabilistic model [Murali et al., 2018].”
A Survey of Machine Learning for Big Code and Naturalness (2017, neutral): “[135] Sketch Synthesis Graphical Model Sketch Mining”
Programmatically Interpretable Reinforcement Learning (2018, methodology): “C ODER (Balog et al., 2016), B AYOU (Murali et al., 2018)), where the network weights are used to guide the program search in a DSL.”
code2vec: learning distributed representations of code (2018, background): “Several works have investigated the properties of source code as bimodal: it is at the same time executable for machines, and readable for humans [Allamanis et al. 2015a, 2016, 2015b; Iyer et al. 2016; Murali et al. 2017; Zilberstein and Yahav 2016].”
Neural Program Synthesis with Priority Queue Training (2018, neutral): “…2016; Zaremba et al., 2016; Barone & Sennrich, 2017; Beltramelli, 2017; Cai et al., 2017; Devlin et al., 2017; Hu et al., 2017; Guu et al., 2017; Johnson et al.; Liang et al., 2017; Murali et al., 2017; Parisotto et al., 2016; Rabinovich et al., 2017; Vigueras et al., 2017; Yin & Neubig, 2017).”
Structural Language Models of Code (2019, background): “C#, but severely restrict the syntax, vocabulary, domain, or nature of the generated programs (Murali et al., 2018; Brockschmidt et al., 2019; Young et al., 2019).”
DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors (2018, background): “Advances in amortized variational inference [1, 2, 3, 4] have enabled novel learning methods [4, 5, 6] and extended generative learning into complex domains such as molecule design [7, 8], music [9] and program [10] generation.”
Synthesizing Environment-Aware Activities via Activity Sketches (2019, methodology): “The work [13] is the most related to ours.”
CODIT: Code Editing With Tree-Based Neural Models (2018, background): “Finally, there are domainspecific approaches, such as error handling code generation [95], [96], API-related changes [9], [10], [11], [12], [13], [14], [97], automatic refactorings [15], [16], [17], [18], etc.”
Learning Programmatic Idioms for Scalable Semantic Parsing (2019, background): “Neural encoder-decoder models have proved effective in mapping NL to logical forms (Dong and Lapata, 2016) and also for directly producing general purpose programs (Iyer et al., 2017, 2018).”
Neurosymbolic Programming (2021, methodology): “For example, one set of methods for neurosymbolic programming uses a neural network to learn to synthesize programs, i.e., direct a search process over program architectures (Balog et al., 2016; Murali et al., 2018).”
SpreadsheetCoder: Formula Prediction from Semi-structured Context (2021, methodology): “To address this, we design a representation for formula sketches inspired by prior work on sketch learning for program synthesis (Solar-Lezama, 2008; Murali et al., 2018; Dong & Lapata, 2018; Nye et al., 2019).”
Learning Compositional Rules via Neural Program Synthesis (2020, methodology): “We are inspired by work such as RobustFill [11], enumerative approaches [16], execution guided work [17, 18, 10, 19], and hybrid models [20, 21].”
CoCoNuT: combining context-aware neural translation models using ensemble for program repair (2020, methodology): “Deep Learning in Software Engineering: The software engineering community had applied deep learning to perform various tasks such as defects prediction [40, 79, 81], source code representation [6, 7, 66, 80], source code summarization [4, 22] source code modeling [5, 11, 26, 83], code clone detectio”
Program Synthesis and Semantic Parsing with Learned Code Idioms (2019, background): “First, recent work [12, 25] has achieved great results by splitting the synthesis process into sketch generation and sketch completion .”
PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context (2021, methodology): “Our design of hierarchical program decoding is inspired by prior work on sketch learning for program synthesis, where various sketch representations have been proposed for different applications (Solar-Lezama, 2008; Murali et al., 2018; Dong and Lapata, 2018; Nye et al., 2019).”