tomaarsen/SpanMarkerNER
A Named Entity Recognition framework built on Hugging Face Transformers using BERT, RoBERTa and ELECTRA encoders.
Not currently ranked — collecting fresh signals.
star history
SpanMarker is a framework for training Named Entity Recognition models based on the PL-Marker paper. It is built on top of Hugging Face Transformers, leveraging pre-trained encoder models such as BERT and RoBERTa for entity span detection. The library supports common annotation schemes (IOB, IO2, BIOES, BILOU), integrates with the Hugging Face Hub for model sharing and inference, and provides features like hyperparameter optimization, mixed precision training, and 8-bit inference.
Frequently asked
- What is tomaarsen/SpanMarkerNER?
- A Named Entity Recognition framework built on Hugging Face Transformers using BERT, RoBERTa and ELECTRA encoders.
- Is SpanMarkerNER open source?
- Yes — tomaarsen/SpanMarkerNER is open source, released under the Apache-2.0 license.
- What language is SpanMarkerNER written in?
- tomaarsen/SpanMarkerNER is primarily written in Jupyter Notebook.
- How popular is SpanMarkerNER?
- tomaarsen/SpanMarkerNER has 476 stars on GitHub.
- Where can I find SpanMarkerNER?
- tomaarsen/SpanMarkerNER is on GitHub at https://github.com/tomaarsen/SpanMarkerNER.