From 9536ee787c730151575bdbc8df407f4f4a3e1199 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Sat, 1 Dec 2018 13:42:18 +0000 Subject: [PATCH] Add comma deletion to data noising --- spacy/gold.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/gold.pyx b/spacy/gold.pyx index 0f25d7f53..26ff9753a 100644 --- a/spacy/gold.pyx +++ b/spacy/gold.pyx @@ -265,7 +265,7 @@ def _corrupt(c, noise_level): return '\n' elif c == '\n': return ' ' - elif c in ['.', "'", "!", "?"]: + elif c in ['.', "'", "!", "?", ',']: return '' else: return c.lower()