How to annotate a corpus to train a SpanFinder


I was wondering how to train a SpanFinder model on its own. I've found the existing example config and corpus referenced in this post, but it's unclear to me how to go about annotating a corpus with unlabelled spans using Prodigy. I know how to train a span_cat model, but at this stage I'd like to train a span_finder to suggest spans that I will classify later.


Sorry for the delay!

This feels like it's mostly a spaCy question though, so it feels best to ask on the spaCy discussion board on Github. You'll be able to interact with the maintainers there and they will be more knowledge-able about the inner details of how to train your own span finder.

1 Like