BERT Onomatopoeia Recognition

This model is a finetuned BERT large model (cased) on a sample of 18 000 manually filtered sentences containing onomatopoeia from the British National Corpus (http://bncweb.lancs.ac.uk/). The model allows to detect onomatopoeia in the form of interjections, nouns, and verbs in any given text.

Model Details

Model Description

• Developed by Szymon Pindur, Jagiellonian University in Krakow
• Model type Token classification
• Language(s) (NLP) English
• Finetuned from model [optional] bert-large-cased (https://huggingface.co/bert-large-cased)