explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-03-22 02:44:15 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix #717: Set correct lemma for contracted verbs

Browse Source
This commit is contained in:
Matthew Honnibal 2017-03-18 16:16:10 +01:00
parent 413138de79
commit fe442cac53
3 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/en/morph_rules.py
View File

@ -54,10 +54,13 @@ MORPH_RULES = {
"am": {LEMMA: "be", "VerbForm": "Fin", "Person": "One", "Tense": "Pres", "Mood": "Ind"}, "am": {LEMMA: "be", "VerbForm": "Fin", "Person": "One", "Tense": "Pres", "Mood": "Ind"},
"are": {LEMMA: "be", "VerbForm": "Fin", "Person": "Two", "Tense": "Pres", "Mood": "Ind"}, "are": {LEMMA: "be", "VerbForm": "Fin", "Person": "Two", "Tense": "Pres", "Mood": "Ind"},
"is": {LEMMA: "be", "VerbForm": "Fin", "Person": "Three", "Tense": "Pres", "Mood": "Ind"}, "is": {LEMMA: "be", "VerbForm": "Fin", "Person": "Three", "Tense": "Pres", "Mood": "Ind"},
"'re": {LEMMA: "be", "VerbForm": "Fin", "Person": "Two", "Tense": "Pres", "Mood": "Ind"},
"'s": {LEMMA: "be", "VerbForm": "Fin", "Person": "Three", "Tense": "Pres", "Mood": "Ind"},
}, },
"VBP": { "VBP": {
"are": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"} "are": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"},
"'re": {LEMMA: "be", "VerbForm": "Fin", "Tense": "Pres", "Mood": "Ind"}
}, },
"VBD": { "VBD": {

2
spacy/en/tokenizer_exceptions.py
View File

@ -107,7 +107,7 @@ for pron in ["you", "we", "they"]:
EXC[orth + "re"] = [ EXC[orth + "re"] = [
{ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"}, {ORTH: orth, LEMMA: PRON_LEMMA, TAG: "PRP"},
{ORTH: "re", LEMMA: "be", NORM: "are"} {ORTH: "re", LEMMA: "be", NORM: "are", TAG: "VBZ"}
] ]

6
spacy/tests/regression/test_issue717.py
View File

@ -4,9 +4,11 @@ from __future__ import unicode_literals
import pytest import pytest
@pytest.mark.xfail
@pytest.mark.models @pytest.mark.models
@pytest.mark.parametrize('text1,text2', [("You're happy", "You are happy")]) @pytest.mark.parametrize('text1,text2',
[("You're happy", "You are happy"),
("I'm happy", "I am happy"),
("he's happy", "he's happy")])
def test_issue717(EN, text1, text2): def test_issue717(EN, text1, text2):
"""Test that contractions are assigned the correct lemma.""" """Test that contractions are assigned the correct lemma."""
doc1 = EN(text1) doc1 = EN(text1)