diff --git a/website/docs/usage/v2-1.md b/website/docs/usage/v2-1.md
index 35ec20f4f..bf9f2e009 100644
--- a/website/docs/usage/v2-1.md
+++ b/website/docs/usage/v2-1.md
@@ -250,9 +250,14 @@ if all of your models are up to date, you can run the
   + data = nlp.tokenizer.to_bytes(exclude=["vocab"])
   ```
 
+- The .pos value for several common English words has changed, due to
+  corrections to long-standing mistakes in the English tag map (see
+  [issue #593](https://github.com/explosion/spaCy/issues/593) and
+  [issue #3311](https://github.com/explosion/spaCy/issues/3311) for details).
+
 - For better compatibility with the Universal Dependencies data, the lemmatizer
   now preserves capitalization, e.g. for proper nouns. See
-  [this issue](https://github.com/explosion/spaCy/issues/3256) for details.
+  [issue #3256](https://github.com/explosion/spaCy/issues/3256) for details.
 
 - The built-in rule-based sentence boundary detector is now only called
   `"sentencizer"` – the name `"sbd"` is deprecated.