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

Generate he/she/it correctly with 's instead of 've

Browse Source
This commit is contained in:
Ines Montani 2017-01-05 19:57:00 +01:00
parent 8328925e1f
commit 7d2cf934b9
1 changed files with 28 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
spacy/en/tokenizer_exceptions.py
View File

@ -7,7 +7,7 @@ from ..language_data import PRON_LEMMA
EXC = {} EXC = {}
EXCLUDE_EXC = ["Ill", "ill", "Hell", "hell", "Well", "well", "Whore", "whore"] EXCLUDE_EXC = ["Ill", "ill", "Its", "its", "Hell", "hell", "Well", "well", "Whore", "whore"]
# Pronouns # Pronouns
@ -49,16 +49,6 @@ for pron in ["i", "you", "he", "she", "it", "we", "they"]:
{ORTH: "ll", LEMMA: "will", TAG: "MD"} {ORTH: "ll", LEMMA: "will", TAG: "MD"}
] ]
EXC[orth + "'ve"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "'ve", LEMMA: "have", TAG: "VB"}
]
EXC[orth + "ve"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "ve", LEMMA: "have", TAG: "VB"}
]
EXC[orth + "'ll've"] = [ EXC[orth + "'ll've"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"}, {ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "'ll", LEMMA: "will", TAG: "MD"}, {ORTH: "'ll", LEMMA: "will", TAG: "MD"},
@ -94,6 +84,19 @@ for pron in ["i", "you", "he", "she", "it", "we", "they"]:
] ]
for pron in ["i", "you", "we", "they"]:
for orth in [pron, pron.title()]:
EXC[orth + "'ve"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "'ve", LEMMA: "have", TAG: "VB"}
]
EXC[orth + "ve"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "ve", LEMMA: "have", TAG: "VB"}
]
for pron in ["you", "we", "they"]: for pron in ["you", "we", "they"]:
for orth in [pron, pron.title()]: for orth in [pron, pron.title()]:
EXC[orth + "'re"] = [ EXC[orth + "'re"] = [
@ -107,6 +110,20 @@ for pron in ["you", "we", "they"]:
] ]
for pron in ["he", "she", "it"]:
for orth in [pron, pron.title()]:
EXC[orth + "'s"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "'s"}
]
EXC[orth + "s"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "s"}
]
# W-words, relative pronouns, prepositions etc. # W-words, relative pronouns, prepositions etc.
for word in ["who", "what", "when", "where", "why", "how", "there", "that"]: for word in ["who", "what", "when", "where", "why", "how", "there", "that"]: