A Grammar-Based Structural CNN Decoder for Code Generation

Component-based synthesis is an important research field in program synthesis. API-based synthesis is a subfield of componentbased synthesis, the component library of which are Java APIs. Unlike existing work in API-based synthesis that can only generate loop-free programs constituted by APIs, state-of-the-art work FrAngel can generate programs with control structures. However, for the generation of control structures, it samples different types of control structures all at random. Given the information about the desired method (such as method name and input/output types), experienced programmers can have an initial thought about the possible control structures that could be used in implementing the desired method. The knowledge about control structures in the method can be learned from high-quality projects. In this paper, we propose a novel approach of recommending control structures for API-based synthesis based on deep learning. A neural network that can jointly embed the natural language description, method name, and input/output types into high-dimensional vectors to predict the possible control structures of the desired method is proposed. We integrate the prediction model into the synthesizer to improve the efficiency of synthesis. We train our model on a codebase of high-quality Java projects from GitHub. The prediction results of the neural network are fed to the API-based synthesizer to guide the sampling process of control structures. The experimental results on 40 programming tasks show that our approach can effectively improve the efficiency of synthesis.

show abstract

“…Gu et al [11] applied deep learning to code search. Sun et al [40] proposed a CNN-based model for code generation.…”

Section: Deep Learning For Source Codementioning

confidence: 99%

Boosting component-based synthesis with control structure recommendation

Liu

Dong

Zhang

et al. 2020

Proceedings of the 1st ACM SIGSOFT International Workshop on Representation Learning for Software Engineering and Program Langu

View full text Add to dashboard Cite

show abstract

“…Rabinovich et al (2017) presented a abstract syntax network that combines edge information for code generation. Convolution neural networks (CNNs) were used for code generation decoding because the output program is much longer than semantic parsing and MWPs, and RNNs suffer from the long dependency problem (Sun et al, 2018).…”

Section: Seq2tree Architecturesmentioning

confidence: 99%

Tree-structured Decoding for Solving Math Word Problems

Liu¹,

Guan²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Automatically solving math word problems is an interesting research topic that needs to bridge natural language descriptions and formal math equations. Previous studies introduced end-to-end neural network methods, but these approaches did not efficiently consider an important characteristic of the equation, i.e., an abstract syntax tree. To address this problem, we propose a tree-structured decoding method that generates the abstract syntax tree of the equation in a top-down manner. In addition, our approach can automatically stop during decoding without a redundant stop token. The experimental results show that our method achieves single model state-of-the-art performance on Math23K, which is the largest dataset on this task.

show abstract

“…The neural network produces distributed representations of inputs and outputs, which are used to pick the appropriate function and corresponding arguments. Sun et al [2018] constrain the search for programs using a neural network by integrating a grammar into their inference procedure. Their neural network learns to select the appropriate grammar production to expand a non-terminal in an intermediate program representation.…”

Section: Neural Program Synthesismentioning

confidence: 99%

“…This approach is closer in spirit to the conditional program generation used in Bayou. Additionally, with the exception of Sun et al [2018], many of these systems have focused on a different domain for evaluation: string manipulation tasks.…”

Section: Neural Program Synthesismentioning

confidence: 99%

AL: autogenerating supervised learning programs

Cambronero

Rinard

2019

Proc. ACM Program. Lang.

View full text Add to dashboard Cite

We present AL, a novel automated machine learning system that learns to generate new supervised learning pipelines from an existing corpus of supervised learning programs. In contrast to existing automated machine learning tools, which typically implement a search over manually selected machine learning functions and classes, AL learns to identify the relevant classes in an API by analyzing dynamic program traces that use the target machine learning library. AL constructs a conditional probability model from these traces to estimate the likelihood of the generated supervised learning pipelines and uses this model to guide the search to generate pipelines for new datasets. Our evaluation shows that AL can produce successful pipelines for datasets that previous systems fail to process and produces pipelines with comparable predictive performance for datasets that previous systems process successfully. CCS Concepts: • Software and its engineering → Automatic programming; • Computing methodologies → Machine learning.

show abstract

A Grammar-Based Structural CNN Decoder for Code Generation

Cited by 98 publications

References 4 publications

Boosting component-based synthesis with control structure recommendation

Boosting component-based synthesis with control structure recommendation

Tree-structured Decoding for Solving Math Word Problems

AL: autogenerating supervised learning programs

Contact Info

Product

Resources

About