We introduce DS-1000, a code generation benchmark with a thousand data science
problems spanning seven Python libraries, such as Numpy and Pandas. Compared to prior …

Code generation is a longstanding challenge, aiming to generate a code snippet based on a
natural language description. Usually, expensive text-code paired data is essential for …

In this work we systematically review the recent advancements in code processing with
language models, covering 50+ models, 30+ evaluation tasks, 170+ datasets, and 700 …

Code generation models can benefit data scientists' productivity by automatically generating
code from context and text descriptions. An important measure of the modeling progress is …

Automatically fixing compilation errors can greatly raise the productivity of software
development, by guiding the novice or AI programmers to write and debug code. Recently …

The increasing use of Large Language Models (LLMs) in software development has
garnered significant attention from researchers assessing the quality of the code they …

Neural Code Intelligence--leveraging deep learning to understand, generate, and optimize
code--holds immense potential for transformative impacts on the whole society. Bridging the …

Data wrangling, the process of preparing raw data for further analysis in computational
notebooks, is a crucial yet time-consuming step in data science. Code generation has the …

Can non-programmers annotate natural language utterances with complex programs that
represent their meaning? We introduce APEL, a framework in which non-programmers …

Recent advances in NLP have led to a rise in inter-disciplinary and application-oriented
research. While this demonstrates the growing real-world impact of the field, research …