From a87b0cc5848bc1a0b8656787e1b3573ba7d8bed6 Mon Sep 17 00:00:00 2001 From: Adriane Boyd Date: Wed, 9 Aug 2023 10:30:50 +0200 Subject: [PATCH] Switch zh tokenizer default pkuseg_model to spacy_ontonotes So that users can use `copy_from_base_model` for other segmenters without having to override an irrelevant `pkuseg_model` setting, switch the default `pkuseg_model` to `spacy_ontonotes`. --- spacy/lang/zh/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/lang/zh/__init__.py b/spacy/lang/zh/__init__.py index f7bb09277..6b980b52b 100644 --- a/spacy/lang/zh/__init__.py +++ b/spacy/lang/zh/__init__.py @@ -31,7 +31,7 @@ segmenter = "char" [initialize] [initialize.tokenizer] -pkuseg_model = null +pkuseg_model = "spacy_ontonotes" pkuseg_user_dict = "default" """