From fe9299a118b107444e88ca9c99dd2c090a0b50eb Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Thu, 14 Apr 2016 12:46:43 +0200 Subject: [PATCH] * Fix long-standing issue with coarse-grained tags: proper nouns weren't receiving the PROPN tag, and personal pronouns weren't receiving the PRON tag. This should fix Issue #191, and also Issue #325, which reported that proper nouns were being lemmatized using the common noun policies. This lemmatization will be prevented if the universal tag is PROPN, not NOUN, as no lemmatization rules are loaded for the PROPN tag. --- lang_data/en/tag_map.json | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/lang_data/en/tag_map.json b/lang_data/en/tag_map.json index a38411bcf..f913f38fe 100644 --- a/lang_data/en/tag_map.json +++ b/lang_data/en/tag_map.json @@ -24,12 +24,12 @@ "MD": {"pos": "verb", "verbtype": "mod"}, "NIL": {"pos": ""}, "NN": {"pos": "noun", "number": "sing"}, -"NNP": {"pos": "noun", "nountype": "prop", "number": "sing"}, -"NNPS": {"pos": "noun", "nountype": "prop", "number": "plur"}, +"NNP": {"pos": "propn", "nountype": "prop", "number": "sing"}, +"NNPS": {"pos": "propn", "nountype": "prop", "number": "plur"}, "NNS": {"pos": "noun", "number": "plur"}, "PDT": {"pos": "adj", "adjtype": "pdt", "prontype": "prn"}, "POS": {"pos": "part", "poss": "poss"}, -"PRP": {"pos": "noun", "prontype": "prs"}, +"PRP": {"pos": "pron", "prontype": "prs"}, "PRP$": {"pos": "adj", "prontype": "prs", "poss": "poss"}, "RB": {"pos": "adv", "degree": "pos"}, "RBR": {"pos": "adv", "degree": "comp"},