Program Synthesis from Natural Language Using Recurrent Neural Networks

By Xi Victoria Lin. 2017

Subfields: Natural Language Processing, Code Generation & Program Synthesis

How researchers see this paper

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

In Natural Language Processing

1. Charles Sutton
2. Miltiadis Allamanis
3. Premkumar T. Devanbu
4. Luke S. Zettlemoyer
5. Earl T. Barr
6. Omer Levy
7. Graham Neubig
8. Xi Victoria Lin

In Code Generation & Program Synthesis

1. Charles Sutton
2. Miltiadis Allamanis
3. Earl T. Barr
4. Premkumar T. Devanbu
5. Michael D. Ernst
6. Luke S. Zettlemoyer
7. Chenglong Wang
8. Erfan Al-Hossami

Citations in the corpus

• A Survey of Machine Learning for Big Code and Naturalness (2017, background): “[106] PD (c |m) Tokens NN (Seq2seq) Synthesis”
• NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System (2018, methodology): “Tellina The stage-wise natural language programing model, Tellina (Lin et al., 2017), first abstracts the constants in an NL to their corresponding semantic types (e.”
• LEVER: Learning to Verify Language-to-Code Generation with Execution (2023, unknown): “…including rule-based systems (Woods, 1973; Templeton & Burger, 1983), structured prediction (Zelle & Mooney, 1996; Zettlemoyer & Collins, 2005; Gulwani & Marron, 2014) and deep learning (Xiao et al., 2016; Dong & Lapata, 2016; Rabinovich et al., 2017; Zhong et al., 2017; Lin et al., 2017).”
• NAPS: Natural Program Synthesis Dataset (2018, background): “Recent examples of crowdsourced natural language to program datasets are WikiSQL (Zhong et al., 2017) and NL2Bash (Lin et al., 2017).”
• Can we generate shellcodes via natural language? An empirical study (2021, methodology): “NMT has also been used to perform complex tasks on the UNIX operating system shell (Lin et al., 2017) (e.”