Code Generation

70 papers with code • 9 benchmarks • 17 datasets

Code Generation is an important field to predict explicit code or program structure from multimodal data sources such as incomplete code, programs in another programming language, natural language descriptions or execution examples. Code Generation tools can assist the development of automatic programming tools to improve programming productivity.

Source: Deep Learning for Source Code Modeling and Generation

Image source: Measuring Coding Challenge Competence With APPS

Greatest papers with code

pix2code: Generating Code from a Graphical User Interface Screenshot

tonybeltramelli/pix2code 22 May 2017

Transforming a graphical user interface screenshot created by a designer into computer code is a typical task conducted by a developer in order to build customized software, websites, and mobile applications.

Code Generation

Stripe: Tensor Compilation via the Nested Polyhedral Model

plaidml/plaidml 14 Mar 2019

Hardware architectures and machine learning (ML) libraries evolve rapidly.

Code Generation

Hierarchical Cost Analysis for Distributed DL

mindspore-ai/mindspore IEEE International Parallel and Distributed Processing Symposium Workshops 2021

In order to formalize the behaviors of the HP in distributed DL and quantitatively evaluate the cost caused by HP, we are studying Bridging DL composed by a double-level execution model associated with a symbolic cost model.

Code Generation

Evaluating Large Language Models Trained on Code

microsoft/PythonProgrammingPuzzles 7 Jul 2021

We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities.

Code Generation Language Modelling

Programming Puzzles

microsoft/PythonProgrammingPuzzles 10 Jun 2021

The dataset is comprehensive in that it spans problems of a range of difficulties and domains, ranging from trivial string manipulation problems, to classic programming puzzles (e. g., Tower of Hanoi), to interview/competitive-programming problems (e. g., dynamic programming), to longstanding open problems in algorithms and mathematics (e. g., factoring).

Code Generation Language understanding +2

FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference

pytorch/fbgemm 13 Jan 2021

Deep learning models typically use single-precision (FP32) floating point data types for representing activations and weights, but a slew of recent research work has shown that computations with reduced-precision data types (FP16, 16-bit integers, 8-bit integers or even 4- or 2-bit integers) are enough to achieve same accuracy as FP32 and are much more efficient.

Code Generation Quantization

Deep Hashing with Category Mask for Fast Video Retrieval

willard-yuan/hashing-baseline-for-image-retrieval 22 Dec 2017

This paper proposes an end-to-end deep hashing framework with category mask for fast video retrieval.

Classification Code Generation +2

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

microsoft/CodeXGLUE 9 Feb 2021

Benchmark datasets have a significant impact on accelerating research in programming language tasks.

Clone Detection Cloze Test +9

TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

pcyin/tranX EMNLP 2018

We present TRANX, a transition-based neural semantic parser that maps natural language (NL) utterances into formal meaning representations (MRs).

Code Generation Semantic Parsing

StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing

pcyin/tranX ACL 2018

Semantic parsing is the task of transducing natural language (NL) utterances into formal meaning representations (MRs), commonly represented as tree structures.

Code Generation Latent Variable Models +1