From 27d306ff5e5ca09d2af6874659f47b4cb86e678b Mon Sep 17 00:00:00 2001
From: John Bauer <horatio@gmail.com>
Date: Sun, 12 Nov 2023 21:10:59 -0800
Subject: [PATCH] Add some documentation on the ontonotes/ww conversion

---
 stanza/utils/datasets/ner/ontonotes_multitag.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/stanza/utils/datasets/ner/ontonotes_multitag.py b/stanza/utils/datasets/ner/ontonotes_multitag.py
index 578a17f568..47d694b1ca 100644
--- a/stanza/utils/datasets/ner/ontonotes_multitag.py
+++ b/stanza/utils/datasets/ner/ontonotes_multitag.py
@@ -1,3 +1,14 @@
+"""
+Combines OntoNotes and WW into a single dataset with OntoNotes used for dev & test
+
+The resulting dataset has two layers saved in the multi_ner column.
+
+WW is kept as 9 classes, with the tag put in either the first or
+second layer depending on the flags.
+
+OntoNotes is converted to one column for 18 and one column for 9 classes.
+"""
+
 import argparse
 import json
 import os