Sahaj.blogs

Day page

4 Jul 2025

Study

NLP · Named entity recognition

NER as token-level sequence labelling with BIO tags, running spaCy's pretrained pipeline, and why entity spans make evaluation tricky.

  • NER labels spans of tokens as people, places, organisations, dates and so on.
  • BIO tags (B-egin, I-nside, O-utside) turn span labelling into per-token classification.

Read the post →