From bab30e4ad2ad35d7133b7f8027a3558a02e018e4 Mon Sep 17 00:00:00 2001 From: Jones Martins Date: Wed, 10 Jun 2020 16:54:06 -0300 Subject: [PATCH] Add "c'mon" token exception (#5570) * Add "c'mon" exception * Fix typo in "C'mon" exception --- spacy/lang/en/tokenizer_exceptions.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/spacy/lang/en/tokenizer_exceptions.py b/spacy/lang/en/tokenizer_exceptions.py index f8367c0f5..964a714ae 100644 --- a/spacy/lang/en/tokenizer_exceptions.py +++ b/spacy/lang/en/tokenizer_exceptions.py @@ -399,6 +399,14 @@ _other_exc = { {ORTH: "Let", LEMMA: "let", NORM: "let"}, {ORTH: "'s", LEMMA: PRON_LEMMA, NORM: "us"}, ], + "c'mon": [ + {ORTH: "c'm", NORM: "come", LEMMA: "come"}, + {ORTH: "on"} + ], + "C'mon": [ + {ORTH: "C'm", NORM: "come", LEMMA: "come"}, + {ORTH: "on"} + ] } _exc.update(_other_exc)