def db_phrase_extract(lang1, lang2,
lang1method=lambda x: x,
lang2method=lambda x: x,
init_val=1.0e-10,
db="sqlite:///:memory:"):
lang1s = lang1method(lang1).split()
lang2s = lang1method(lang2).split()
alignment = _db_symmetrization(lang1s, lang2s,
init_val=init_val,
db=db)
return phrase_extract.phrase_extract(lang1s, lang2s, alignment)
def test_phrase_extract(self):
# next alignment matrix is like
#
# |x| | | | | | | | | |
# | |x|x|x| | | | | | |
# | | | | | |x| | | | |
# | | | | | | |x| | | |
# | | | | | | | | | |x|
# | | | | | | | | | |x|
# | | | | | | | |x| | |
# | | | | | | | |x| | |
# | | | | | | | | |x| |
#
es = "michael assumes that he will stay in the house".split()
fs = "michael geht davon aus , dass er im haus bleibt".split()
alignment = set([(1, 1), (2, 2), (2, 3), (2, 4), (3, 6), (4, 7),
(5, 10), (6, 10), (7, 8), (8, 8), (9, 9)])
ans = set([
(('assumes', ), ('geht', 'davon', 'aus')),
(('assumes', ), ('geht', 'davon', 'aus', ',')),
(('assumes', 'that'), ('geht', 'davon', 'aus', ',', 'dass')),
(('assumes', 'that', 'he'), ('geht', 'davon', 'aus', ',', 'dass',
'er')),
(('assumes', 'that', 'he', 'will', 'stay', 'in', 'the', 'house'),
('geht', 'davon', 'aus', ',', 'dass', 'er', 'im', 'haus',
'bleibt')), (('he', ), ('er', )),
(('he', 'will', 'stay', 'in', 'the', 'house'), ('er', 'im', 'haus',
'bleibt')),
(('house', ), ('haus', )), (('in', 'the'), ('im', )),
(('in', 'the', 'house'), ('im', 'haus')),
(('michael', ), ('michael', )),
(('michael', 'assumes'), ('michael', 'geht', 'davon', 'aus')),
(('michael', 'assumes'), ('michael', 'geht', 'davon', 'aus', ',')),
(('michael', 'assumes', 'that'), ('michael', 'geht', 'davon',
'aus', ',', 'dass')),
(('michael', 'assumes', 'that', 'he'), ('michael', 'geht', 'davon',
'aus', ',', 'dass', 'er')),
(('michael', 'assumes', 'that', 'he', 'will', 'stay', 'in', 'the',
'house'), ('michael', 'geht', 'davon', 'aus', ',', 'dass', 'er',
'im', 'haus', 'bleibt')), (('that', ), (',', 'dass')),
(('that', ), ('dass', )), (('that', 'he'), (',', 'dass', 'er')),
(('that', 'he'), ('dass', 'er')),
(('that', 'he', 'will', 'stay', 'in', 'the', 'house'),
(',', 'dass', 'er', 'im', 'haus', 'bleibt')),
(('that', 'he', 'will', 'stay', 'in', 'the', 'house'),
('dass', 'er', 'im', 'haus', 'bleibt')),
(('will', 'stay'), ('bleibt', )),
(('will', 'stay', 'in', 'the', 'house'), ('im', 'haus', 'bleibt'))
])
self.assertEqual(phrase_extract(es, fs, alignment), ans)
# another test
es, fs = ("私 は 先生 です".split(), "I am a teacher".split())
sentenses = [
("僕 は 男 です", "I am a man"),
("私 は 女 です", "I am a girl"),
("私 は 先生 です", "I am a teacher"),
("彼女 は 先生 です", "She is a teacher"),
("彼 は 先生 です", "He is a teacher"),
]
corpus = mkcorpus(sentenses)
alignment = symmetrization(es, fs, corpus)
ans = set([(('\xe3\x81\xaf', '\xe5\x85\x88\xe7\x94\x9f',
'\xe3\x81\xa7\xe3\x81\x99'), ('a', 'teacher')),
(('\xe5\x85\x88\xe7\x94\x9f', ), ('teacher', )),
(('\xe7\xa7\x81', ), ('I', 'am')),
(('\xe7\xa7\x81', '\xe3\x81\xaf',
'\xe5\x85\x88\xe7\x94\x9f', '\xe3\x81\xa7\xe3\x81\x99'),
('I', 'am', 'a', 'teacher'))])
self.assertEqual(phrase_extract(es, fs, alignment), ans)
def test_phrase_extract(self):
# next alignment matrix is like
#
# |x| | | | | | | | | |
# | |x|x|x| | | | | | |
# | | | | | |x| | | | |
# | | | | | | |x| | | |
# | | | | | | | | | |x|
# | | | | | | | | | |x|
# | | | | | | | |x| | |
# | | | | | | | |x| | |
# | | | | | | | | |x| |
#
es = "michael assumes that he will stay in the house".split()
fs = "michael geht davon aus , dass er im haus bleibt".split()
alignment = set([(1, 1),
(2, 2),
(2, 3),
(2, 4),
(3, 6),
(4, 7),
(5, 10),
(6, 10),
(7, 8),
(8, 8),
(9, 9)])
ans = set([(('assumes',), ('geht', 'davon', 'aus')),
(('assumes',), ('geht', 'davon', 'aus', ',')),
(('assumes', 'that'),
('geht', 'davon', 'aus', ',', 'dass')),
(('assumes', 'that', 'he'),
('geht', 'davon', 'aus', ',', 'dass', 'er')),
(('assumes', 'that', 'he',
'will', 'stay', 'in', 'the', 'house'),
('geht', 'davon', 'aus', ',', 'dass',
'er', 'im', 'haus', 'bleibt')),
(('he',), ('er',)),
(('he', 'will', 'stay', 'in', 'the', 'house'),
('er', 'im', 'haus', 'bleibt')),
(('house',), ('haus',)),
(('in', 'the'), ('im',)),
(('in', 'the', 'house'), ('im', 'haus')),
(('michael',), ('michael',)),
(('michael', 'assumes'),
('michael', 'geht', 'davon', 'aus')),
(('michael', 'assumes'),
('michael', 'geht', 'davon', 'aus', ',')),
(('michael', 'assumes', 'that'),
('michael', 'geht', 'davon', 'aus', ',', 'dass')),
(('michael', 'assumes', 'that', 'he'),
('michael', 'geht', 'davon', 'aus', ',', 'dass', 'er')),
(('michael',
'assumes',
'that',
'he',
'will',
'stay',
'in',
'the',
'house'),
('michael',
'geht',
'davon',
'aus',
',',
'dass',
'er',
'im',
'haus',
'bleibt')),
(('that',), (',', 'dass')),
(('that',), ('dass',)),
(('that', 'he'), (',', 'dass', 'er')),
(('that', 'he'), ('dass', 'er')),
(('that', 'he', 'will', 'stay', 'in', 'the', 'house'),
(',', 'dass', 'er', 'im', 'haus', 'bleibt')),
(('that', 'he', 'will', 'stay', 'in', 'the', 'house'),
('dass', 'er', 'im', 'haus', 'bleibt')),
(('will', 'stay'), ('bleibt',)),
(('will', 'stay', 'in', 'the', 'house'),
('im', 'haus', 'bleibt'))])
self.assertEqual(phrase_extract(es, fs, alignment), ans)
# another test
es, fs = ("私 は 先生 です".split(), "I am a teacher".split())
sentenses = [("僕 は 男 です", "I am a man"),
("私 は 女 です", "I am a girl"),
("私 は 先生 です", "I am a teacher"),
("彼女 は 先生 です", "She is a teacher"),
("彼 は 先生 です", "He is a teacher"),
]
corpus = mkcorpus(sentenses)
alignment = symmetrization(es, fs, corpus)
ans = set([(('\xe3\x81\xaf',
'\xe5\x85\x88\xe7\x94\x9f',
'\xe3\x81\xa7\xe3\x81\x99'),
('a', 'teacher')),
(('\xe5\x85\x88\xe7\x94\x9f',), ('teacher',)),
(('\xe7\xa7\x81',), ('I', 'am')),
(('\xe7\xa7\x81',
'\xe3\x81\xaf',
'\xe5\x85\x88\xe7\x94\x9f',
'\xe3\x81\xa7\xe3\x81\x99'),
('I', 'am', 'a', 'teacher'))])
self.assertEqual(phrase_extract(es, fs, alignment), ans)