# Semantic Code Classification for Automated Machine Learning

arXiv: https://arxiv.org/abs/2201.11252 · HTML: https://mlsanity.com/paper/2201.11252/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 25 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [BPE-Dropout: Simple and Effective Subword Regularization](https://mlsanity.com/paper/1910.13267/) (2019)
- [PyMT5: multi-mode translation of natural language and Python code with transformers](https://mlsanity.com/paper/2010.03150/) (2020)
- [In-IDE Code Generation from Natural Language: Promise and Challenges](https://mlsanity.com/paper/2101.11149/) (2021)
- [Naive Bayes and Text Classification I - Introduction and Theory](https://mlsanity.com/paper/1410.5329/) (2014)

## Abstract (arXiv)

A range of applications for automatic machine learning need the generation process to be controllable. In this work, we propose a way to control the output via a sequence of simple actions, that are called semantic code classes. Finally, we present a semantic code classification task and discuss methods for solving this problem on the Natural Language to Machine Learning (NL2ML) dataset.