An ensemble model for classifying idioms and literal texts using BERT and RoBERTa

•Fundamental NLP categorizes text into structured categories.•We propose a predictive ensemble model to classify idioms and literals.•We user BERT and RoBERTa, fine-tuned with the Trofi dataset.•Model is tested with a newly created dataset of idioms and literal expressions, numbering 1470 in all, and annotated by domain experts.