Divide-and-Conquer Approach for Multi-phase Statistical Migration for Source Code (T)

By Anh Tuan Nguyen, Tung Thanh Nguyen, Tien Nhut Nguyen. 2015

91 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Program Analysis & Verification, Software Engineering

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

1. Nan Duan
2. Xinyun Chen
3. Daya Guo
4. Dawn Song
5. Premkumar T. Devanbu
6. Miltiadis Allamanis
7. Baishakhi Ray
8. Graham Neubig

In Information Systems

1. Miltiadis Allamanis
2. Premkumar T. Devanbu
3. Michael Pradel
4. Daya Guo
5. Baishakhi Ray
6. Nan Duan
7. Charles Sutton
8. Tien Nhut Nguyen

In Program Analysis & Verification

1. Miltiadis Allamanis
2. Baishakhi Ray
3. Yangruibo Ding
4. Saikat Chakraborty
5. Tien Nhut Nguyen
6. Xinyun Chen
7. Nan Duan
8. Daya Guo

In Software Engineering

1. Xinyun Chen
2. Dawn Song
3. Chang Liu
4. Miltiadis Allamanis

Citations in the corpus

• CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation (2021, methodology): “[48], we conservatively search for the functions having the same signatures in the classes with the same/similar names and included in the same/similar directory structures of both Java and C# versions.”
• CodeBLEU: a Method for Automatic Evaluation of Code Synthesis (2020, background): “Following Nguyen, Nguyen, and Nguyen (2015) and Chen, Liu, and Song (2018) Human - Table 1: The systems we choose for each task.”
• GraphCodeBERT: Pre-training Code Representations with Data Flow (2020, methodology): “ of our pre-trained model for the task of code clone detection. 5.3 CODE TRANSLATION Code translation aims to migrate legacy software from one programming language in a platform to another. Following Nguyen et al. (2015) and Chen et al. (2018), we conduct experiments on a dataset crawled from the sa”
• Tree-to-tree Neural Networks for Program Translation (2018, methodology): “Note that the program accuracy is an underestimation of the true accuracy based on semantic equivalence, and this metric has been used in [22].”
• Recovering clear, natural identifiers from obfuscated JS names (2017, background): “In follow-up work, they propose several such models aimed at migration of API usages [33, 35, 36].”
• 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].”
• Exploring API Embedding for API Usages and Applications (2017, methodology): “Our prior work SLAMC [40] provides a code representation for our phrase-based SMT models in mppSMT [41] and semSMT [42].”