explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update intro [ci skip]

Browse Source
This commit is contained in:
Ines Montani 2021-06-24 22:53:20 +10:00
parent 68721af628
commit 0d2e2b59bc
1 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
website/docs/usage/v3-1.md
View File

@ -10,14 +10,13 @@ menu:
It's been great to see the adoption of the new spaCy v3, which introduced
[transformer-based](/usage/embeddings-transformers) pipelines, a new
[config and training system](/usage/training) for reproducible experiments, a
new [projects system](/usage/projects) for end-to-end workflows, and many
[other features](/usage/v3). Version 3.1 adds a bunch of new features on top of
it, including the ability to use predicted annotations during training, a new
`SpanCategorizer` component for predicting arbitrary and potentially overlapping
spans, support for partial incorrect annotations in the entity recognizer, new
trained pipelines for Catalan and Danish, as well as many other bug fixes and
improvements.
[config and training system](/usage/training) for reproducible experiments,
[projects](/usage/projects) for end-to-end workflows, and many
[other features](/usage/v3). Version 3.1 adds more on top of it, including the
ability to use predicted annotations during training, a new `SpanCategorizer`
component for predicting arbitrary and potentially overlapping spans, support
for partial incorrect annotations in the entity recognizer, new trained
pipelines for Catalan and Danish, as well as many bug fixes and improvements.
### Using predicted annotations during training {#predicted-annotations-training}