Example of a text snippet showing overlapping spans, such as "bacteremia" being a "Condition", but also part of a larger phrase labeled as "Factor": "bacteremia originating from lower respiratory tract infection".

Spancat: a new approach for span labeling

The SpanCategorizer is a new spaCy component that answers the NLP community’s need to have structured annotation for a wide variety of labeled spans, including long phrases, non-named entities, or overlapping annotations. In this blog post, we talk more about spancat and showcase new features to help with your span labeling needs!

→  Authors: Edward Schmuhl, Lj Miranda, Ákos Kádár, Sofie Van Landeghem, Adriane Boyd

→  Blog post: Full post

→  API: spaCy docs