Spoc: Search-based pseudocode to code
We consider the task of mapping pseudocode to executable code, assuming a one-to-one
correspondence between lines of pseudocode and lines of code. Given test cases as a …
correspondence between lines of pseudocode and lines of code. Given test cases as a …
Learning to generate pseudo-code from source code using statistical machine translation
Pseudo-code written in natural language can aid the comprehension of source code in
unfamiliar programming languages. However, the great majority of source code has no …
unfamiliar programming languages. However, the great majority of source code has no …
Codet: Code generation with generated tests
The task of generating code solutions for a given programming problem can benefit from the
use of pre-trained language models such as Codex, which can produce multiple diverse …
use of pre-trained language models such as Codex, which can produce multiple diverse …
Retrieval-based neural code generation
In models to generate program source code from natural language, representing this code in
a tree structure has been a common approach. However, existing methods often fail to …
a tree structure has been a common approach. However, existing methods often fail to …
Write, execute, assess: Program synthesis with a repl
We present a neural program synthesis approach integrating components which write,
execute, and assess code to navigate the search space of possible programs. We equip the …
execute, and assess code to navigate the search space of possible programs. We equip the …
Fine-grained pseudo-code generation method via code feature extraction and transformer
Pseudo-code written by natural language is helpful for novice developers' program
comprehension. However, writing such pseudo-code is time-consuming and laborious …
comprehension. However, writing such pseudo-code is time-consuming and laborious …
Docprompting: Generating code by retrieving the docs
Publicly available source-code libraries are continuously growing and changing. This makes
it impossible for models of code to keep current with all available APIs by simply training …
it impossible for models of code to keep current with all available APIs by simply training …
Neural program search: Solving programming tasks from description and examples
I Polosukhin, A Skidanov - arXiv preprint arXiv:1802.04335, 2018 - arxiv.org
We present a Neural Program Search, an algorithm to generate programs from natural
language description and a small number of input/output examples. The algorithm combines …
language description and a small number of input/output examples. The algorithm combines …
Neural sketch learning for conditional program generation
We study the problem of generating source code in a strongly typed, Java-like programming
language, given a label (for example a set of API calls or types) carrying a small amount of …
language, given a label (for example a set of API calls or types) carrying a small amount of …
Learning to infer program sketches
Our goal is to build systems which write code automatically from the kinds of specifications
humans can most easily provide, such as examples and natural language instruction. The …
humans can most easily provide, such as examples and natural language instruction. The …