Program Language Translation Using a Grammar-Driven Tree-to-Tree Model

Drissi, Mehdi; Watkins, Olivia; Khant, Aditya; Ojha, Vivaswat; Sandoval, Pedro; Segev, Rakia; Weiner, Eric J.; Keller, R.

doi:10.48550/arxiv.1807.01784

Cited by 3 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input form of the T2Seq is a tree structure and the output is the traversal sequence of AST nodes. • Tree-to-Tree-grammar Model (T2T+Grammar): Drissi et al [37] improved the decoding method on the basis of T2T. This model added grammar rules of the target language to constrain the model to generate programs grammatically correct.…”

Section: Baselinementioning

confidence: 99%

“…They also incorporate the concept of parent attention feeding to enhance the accuracy of prediction results. Based on the Tree-to-Tree model [23], Drissi et al [37] added syntax rules as limitation at each time step during decoding to enforce grammatical correctness in program generation. Lin et al [38] masked the path of abstract syntax tree in pre-training and required model recovery.…”

Section: Abstract Syntax Tree-based Program Translationmentioning

confidence: 99%

“…• Accuracy [37]: calculated on the test set by counting the percentage of perfect results. • Modified nodes: calculated as the number of nodes the software engineer needs to correct in order to get the perfectly correct translation results.…”

Section: Other Metricsmentioning

confidence: 99%

See 2 more Smart Citations

Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree

Zhang,

Liu,

et al. 2023

Preprint

View full text Add to dashboard Cite

Program translation involves converting one programming language into another, which can modernize and migrate applications across platforms. Most of the current program translation methods are sequence-based, which cannot capture the semantic information of the code. To overcome this, abstract syntax tree-based program translation rises up. However, even the state-of-the-art machine translation methods can not guarantee error-free translation results. Consequently, software engineers need to make corrections on the machine's results before using, which is labor-intensive. To solve this problem, we propose the Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree (HMPT-AST), which feeds the human's modification into the model in each iteration and the model updates the result based on human's feedback. It enables two patterns of human participation: First-error-based and Layer-based HMPT-AST. In the former one, the software engineer corrects one error node in each iteration. In the latter one, all error nodes within the same layer are corrected. In addition, the proposed method can also reduce the interactive response time from two aspects: avoiding generating the correct AST subtree repeatedly with parameter cache module, as well as reducing the generation of unnecessary AST subtree with early termination module. We conducted experiments on multiple dataset. The results show that compared with baselines, our method reduces the human effort up to 94.44\% and reduces the response time up to 94.32\%. We have made the code publicly available.\footnote{https://drive.google.com/drive/folders/1878Or6cEsW21fu_cpdpnv_dGevfFr9mB?usp=sharing}

show abstract

Section: Baselinementioning

confidence: 99%

Section: Abstract Syntax Tree-based Program Translationmentioning

confidence: 99%

See 1 more Smart Citation

Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree

Zhang,

Liu,

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A technique known as tree-to-tree encoding and decoding uses parse trees and deep neural networks to convert source code from one language to another [12]. This approach includes a training phase to enhance the encoding process.…”

Section: Related Workmentioning

confidence: 99%

GAST: A generic AST representation for language-independent source code analysis

Leiton-Jimenez,

Barboza-Artavia,

Gonzalez-Torres

et al. 2023

Enfoque UTE

View full text Add to dashboard Cite

Organizations use various programming languages to develop their systems. These aim to take advantage of the most appropriate features of each language for a given domain and require programmers to command different languages and also to face the growing complexity of software development and maintenance. So, they need tools to help them analyze programs to identify relationships between their internal elements, uncover patterns, and calculate quality metrics. However, most tools have limited support for parsing multiple programming languages and high acquisition costs. Therefore, there is a need for new methods to analyze code written in multiple programming languages. This article describes the design of a method to automatically transform the syntax of various programming languages into a universal language with a generic syntax. The function of the generic language is to encapsulate the specificities of each specific language, so that the analysis of programs is facilitated in a single programming syntax and not in multiple syntaxes. The advantage of this approach is that only one analysis engine is required, not multiple code analyzers, to study the programs.

show abstract

“…Among them, Chen et al (2018) used the attention mechanism to locate the corresponding subtree in the source tree and used the information of the subtree to guide the non-terminal extension. Drissi et al (2018) used grammar rules of the target language to generate grammatically correct programs. Ahmad et al (2022) used program summaries as an intermediate language and perform a reverse translation similar to target-to-NL-to-source generation to train the model.…”

Section: Translation Of Programming Languagesmentioning

confidence: 99%

HMPT: a human–machine cooperative program translation method

Zhang,

Yu,

Liu

et al. 2023

Autom Softw Eng

View full text Add to dashboard Cite

Program translation aims to translate one kind of programming language to another, e.g., from Python to Java. Due to the inefficiency of translation rules construction with pure human effort (software engineer) and the low quality of machine translation results with pure machine effort, it is suggested to implement program translation in a human–machine cooperative way. However, existing human–machine program translation methods fail to utilize the human’s ability effectively, which require human to post-edit the results (i.e., statically modified directly on the model generated code). To solve this problem, we propose HMPT (Human-Machine Program Translation), a novel method that achieves program translation based on human–machine cooperation. It can (1) reduce the human effort by introducing a prefix-based interactive protocol that feeds the human’s edit into the model as the prefix and regenerates better output code, and (2) reduce the interactive response time resulted by excessive program length in the regeneration process from two aspects: avoiding duplicate prefix generation with cache attention information, as well as reducing invalid suffix generation by splicing the suffix of the results. The experiments are conducted on two real datasets. Results show compared to the baselines, our method reduces the human effort up to 73.5% at the token level and reduces the response time up to 76.1%.

show abstract

Program Language Translation Using a Grammar-Driven Tree-to-Tree Model

Cited by 3 publications

References 0 publications

Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree

Human-Machine Cooperative Program Translation Based on Abstract Syntax Tree

GAST: A generic AST representation for language-independent source code analysis

HMPT: a human–machine cooperative program translation method

Contact Info

Product

Resources

About