Phrase-Based Statistical Translation of Programming Languages

By Svetoslav Karaivanov, Veselin Raychev, Martin T. Vechev. 2014

147 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Program Synthesis with Large Language Models (2021, methodology): “Porting programs across languages has been treated as a learning problem similar to machine translation [Roziere et al., 2020, Nguyen et al., 2013, Karaivanov et al., 2014].”
A Survey of Machine Learning for Big Code and Naturalness (2017, background): “These types of models have found application within code migration [2, 102, 141], pseudocode generation [146], and code fixing [160].”
CodeBLEU: a Method for Automatic Evaluation of Code Synthesis (2020, methodology): “Along with the rapid progress of code synthesis such as text-to-code synthesis, code translation and code change prediction (Karaivanov, Raychev, and Vechev 2014; Oda et al. 2015; Barone and Sennrich 2017; Chen, Liu, and Song 2018; Kanade et al. 2019; Husain et al. 2019; Feng et al. 2020; Dinella…”
Unsupervised Translation of Programming Languages (2020, methodology): “The majority of studies in source code translation use the BLEU score to evaluate the quality of generated functions [1, 10, 22, 36], or other metrics based on the relative overlap between the tokens in the translation and in the reference.”
Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation (T) (2015, neutral): “While PBMT’s mechanism of translating and reordering short phrases is simple, it also lacks the expressive power to intuitively model pseudo-code generation.”
A Convolutional Attention Network for Extreme Summarization of Source Code (2016, background): “Research has mostly focused on token-level (Nguyen et al., 2013; Tu et al., 2014) and syntax-level (Maddison & Tarlow, 2014) language models of code and translation between programming languages (Karaivanov et al., 2014; Nguyen et al., 2014).”
GraphCodeBERT: Pre-training Code Representations with Data Flow (2020, methodology): “PBSMT is short for phrase-based statistical machine translation (Koehn et al., 2003), and has been exploited in previous works (Nguyen et al., 2013; Karaivanov et al., 2014).”
Tree-to-tree Neural Networks for Program Translation (2018, methodology): “Note that all existing program translation works [16, 22, 21] also study the problem under such an assumption.”
Multi-lingual Evaluation of Code Generation Models (2022, background): “Earlier works (Nguyen et al., 2013; Karaivanov et al., 2014) focused on building semi-automatic tools to find similar functions in Java and C# from open source projects.”
Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code (2020, background): “Precise scoring of code fragments is essential for tasks such as translating a program from one programming language to another [54, 66], code completion [32, 76], and code synthesis from natural language and vice versa [7, 27, 67, 73].”
Program Synthesis from Natural Language Using Recurrent Neural Networks (2017, background): “Recently, machine learning techniques have been developed to build probabilistic models to represent the joint distribution of text and programs [5, 10, 13].”
Statistical Deobfuscation of Android Applications (2016, methodology): “Examples of such tasks include machine translation between programming languages [18], statistical code synthesis [32, 30], and predicting names and types in source code [31, 9].”
Deep learning type inference (2018, background): “Other applications include deobfuscation [10], coding conventions [7, 28] and migration [21, 25].”
New Initiative: The Naturalness of Software (2015, background): “More recent work has moved beyond lexemebased translation to learning phrase-based translation [10].”
Maybe Deep Neural Networks are the Best Choice for Modeling Source Code (2019, methodology): “A generative model for code called probabilistichigher order grammar(PHOG)was introducedby [12], which generalizes probabilistic context free grammars [44].”
CODIT: Code Editing With Tree-Based Neural Models (2018, methodology): “MT is used to translate source code from one programming language into another [66], [67], [68], [69].”
On the naturalness of software (2016, background): “Karaivanov et al. 20 have followed the above work in a similar vein.”