From 28d63ec58e525fe98c230c270a6e0db6e0ac9da2 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Sun, 18 Dec 2016 05:34:51 +0100 Subject: [PATCH] Restore missing '' character in tokenizer exceptions. --- spacy/en/language_data.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/spacy/en/language_data.py b/spacy/en/language_data.py index 8933e1f47..78ec4c19f 100644 --- a/spacy/en/language_data.py +++ b/spacy/en/language_data.py @@ -2214,5 +2214,6 @@ ORTH_ONLY = [ "w.", "x.", "y.", - "z." + "z.", + "''" ]