Updated documentation

tsproisl · Jun 17, 2020 · 01dc552 · 01dc552
1 parent e1ea43f
commit 01dc552
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 2 deletions.
diff --git a/doc/build/markdown/somajo.md b/doc/build/markdown/somajo.md
@@ -32,7 +32,10 @@ Tokenization and sentence splitting.
 
 
     * **xml_sentences** (*str, (default=None)*) – Delimit sentences by XML tags of this name
-    (`xml_sentences='s'` → <s>…</s>).
+    (`xml_sentences='s'` → <s>…</s>). When used with XML input,
+    this might lead to minor changes to the original tags to
+    guarantee well-formed output (tags might need to be closed and
+    re-opened at sentence boundaries).
 
 
 #### tokenize_text(paragraphs, \*, parallel=1)

diff --git a/somajo/somajo.py b/somajo/somajo.py
@@ -24,7 +24,10 @@ class SoMaJo:
         Perform sentence splitting in addition to tokenization.
     xml_sentences : str, (default=None)
         Delimit sentences by XML tags of this name
-        (``xml_sentences='s'`` → <s>…</s>).
+        (``xml_sentences='s'`` → <s>…</s>). When used with XML input,
+        this might lead to minor changes to the original tags to
+        guarantee well-formed output (tags might need to be closed and
+        re-opened at sentence boundaries).
 
     """