Leveraging Automated Machine Learning for Text Classification
Matthias Blohm, Marc Hanussek, Maximilien Kintz
Abstract
Recently, Automated Machine Learning (AutoML) has registered increasing success with respect to tabular data.However, the question arises whether AutoML can also be applied effectively to text classification tasks.This work compares four AutoML tools on 13 different popular datasets, including Kaggle competitions, and opposes human performance.The results show that the AutoML tools perform better than the machine learning community in 4 out of 13 tasks and that two stand out. RELATED WORKAutoML services optimized for NLP tasks like Amazon Comprehend (Mishra) already exist on the market.While these products are specialized in solving problems of text classification or named entity recognition, popular open source tools like