From f0917b6808ef49c1ff1ee0b02a03ea230d20ae20 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Fri, 4 Nov 2016 15:21:28 +0100 Subject: [PATCH] Fix Issue #376: and/or was tagged as a noun. --- spacy/en/language_data.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/spacy/en/language_data.py b/spacy/en/language_data.py index 4666c0c6f..3c9db8fe2 100644 --- a/spacy/en/language_data.py +++ b/spacy/en/language_data.py @@ -112,6 +112,12 @@ TOKENIZER_INFIXES = (r'''\.\.\.+ (?<=[a-z])\.(?=[A-Z]) (?<=[a-zA-Z])-(?=[a-zA-z] TOKENIZER_EXCEPTIONS = { + "and/or": [ + { + "F": "and/or", + "L": "and/or", + "pos": "CC" + }], "Ph.D.": [ { "F": "Ph.D."