Synthesizing Java expressions from free-form queries

By Tihomir Gvero, Viktor Kunčak. 2015

93 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Natural Language Processing

Citations in the corpus

A Survey of Machine Learning for Big Code and Naturalness (2017, background): “Gvero and Kuncak [82] PD (c) Syntax PCFG + Search Code Synthesis”
code2vec: learning distributed representations of code (2018, background): “…et al. 2016], Conditional Random Fields [Raychev et al. 2015], Probabilistic Context-Free Grammars [Allamanis and Sutton 2014; Bielik et al. 2016; Gvero and Kuncak 2015; Maddison and Tarlow 2014], n-grams [Allamanis et al. 2014; Allamanis and Sutton 2013; Hindle et al. 2012; Nguyen et al. 2013;…”
Machine Translation from Natural Language to Code using Long-Short Term Memory (2019, methodology): “r K. developed an Integrated Development Environment (IDE) integrated code assistant tool anyCode for Java which can search, import and call function just by typing desired functionality through text [4]. They have used model and mapping framework between function signatures and utilized resources l”
Exploring API Embedding for API Usages and Applications (2017, methodology): “Anycode [30] uses a probabilistic CFG for Java constructs to synthesize Java expressions.”
Component-based synthesis for complex APIs (2017, background): “Code completion refers to the generation of small code snippets involving API calls [18–20, 24, 30, 37, 39, 41, 49, 53].”
PHOG: Probabilistic Model for Code (2016, background): “Gvero et al., (2015a) augment grammar production rules with additional semantic checks that allow picking local variables in the current scope.”
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): “These models are then used for novel applications such as code completion [32], generating code from natural language [17, 10], sampling code snippets [27], programming language translation [18], type annotating programs [19, 31] and others.”