Semantic Code Classification for Automated Machine Learning
This work addresses the need for controllability in AutoML applications, but appears incremental as it builds on existing datasets and classification approaches.
The paper tackles the problem of controlling automated machine learning (AutoML) outputs by introducing semantic code classes as a sequence of simple actions, and presents a semantic code classification task with methods evaluated on the NL2ML dataset.
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.