explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* 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.

Browse Source
This commit is contained in:
Matthew Honnibal 2016-04-14 12:46:43 +02:00
parent 6f82065761
commit fe9299a118
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lang_data/en/tag_map.json
View File

@ -24,12 +24,12 @@
"MD": {"pos": "verb", "verbtype": "mod"}, "MD": {"pos": "verb", "verbtype": "mod"},
"NIL": {"pos": ""}, "NIL": {"pos": ""},
"NN": {"pos": "noun", "number": "sing"}, "NN": {"pos": "noun", "number": "sing"},
"NNP": {"pos": "noun", "nountype": "prop", "number": "sing"}, "NNP": {"pos": "propn", "nountype": "prop", "number": "sing"},
"NNPS": {"pos": "noun", "nountype": "prop", "number": "plur"}, "NNPS": {"pos": "propn", "nountype": "prop", "number": "plur"},
"NNS": {"pos": "noun", "number": "plur"}, "NNS": {"pos": "noun", "number": "plur"},
"PDT": {"pos": "adj", "adjtype": "pdt", "prontype": "prn"}, "PDT": {"pos": "adj", "adjtype": "pdt", "prontype": "prn"},
"POS": {"pos": "part", "poss": "poss"}, "POS": {"pos": "part", "poss": "poss"},
"PRP": {"pos": "noun", "prontype": "prs"}, "PRP": {"pos": "pron", "prontype": "prs"},
"PRP$": {"pos": "adj", "prontype": "prs", "poss": "poss"}, "PRP$": {"pos": "adj", "prontype": "prs", "poss": "poss"},
"RB": {"pos": "adv", "degree": "pos"}, "RB": {"pos": "adv", "degree": "pos"},
"RBR": {"pos": "adv", "degree": "comp"}, "RBR": {"pos": "adv", "degree": "comp"},