explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-27 12:23:42 +03:00
Code Issues Packages Projects Releases Wiki Activity

Change exactly one -> at most one

Browse Source
This commit is contained in:
Lj Miranda 2023-01-17 10:27:59 +08:00
parent 02ffe45770
commit 52723db6c5
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
website/docs/api/spancategorizer.mdx
View File

@ -16,7 +16,7 @@ that predicts zero or more labels for each candidate.
This component comes in two forms: `spancat` and `spancat_exclusive`. When you This component comes in two forms: `spancat` and `spancat_exclusive`. When you
need to perform multi-label classification on your spans, use `spancat`. The need to perform multi-label classification on your spans, use `spancat`. The
`spancat` component uses a `Logistic` layer where the output class probabilities `spancat` component uses a `Logistic` layer where the output class probabilities
are independent for each class. However, if you need to predict exactly one true are independent for each class. However, if you need to predict at most one true
class for a span, then use `spancat_exclusive`. It uses a `Softmax` layer and class for a span, then use `spancat_exclusive`. It uses a `Softmax` layer and
treats the entities as a multi-class problem. treats the entities as a multi-class problem.