What AI says about SpanMarker

SpanMarker is a framework for training powerful Named Entity Recognition models using familiar encoders such as BERT, RoBERTa and ELECTRA, built on top of the Hugging Face Transformers library. It works out of the box with common encoders (e.g., bert-base-cased, roberta-large) and supports IOB, IOB2, BIOES, BILOU, or no label annotation schemes. It provides end-to-end tooling for training, inference, evaluation, dataset loading, and model deployment to the Hugging Face Hub, with spaCy integration and was developed as part of a thesis at Argilla.