def test_passive(self):
drs = Drs.create_from_natural_language('the rabbit is eaten by me')
expected_drs = Drs.create_from_predicates_string(
"{'entity': '', 'compound': 'rabbit', 'word': 'rabbit', 'tag': 'n'}(v1), {'entity': '', 'compound': 'eaten', 'word': 'eaten', 'tag': 'v'}(v3), {'entity': '', 'compound': 'me', 'word': 'me', 'tag': 'PRP'}(v5), {'type': 'PATIENT'}(v3,v1), {'type': 'AGENT'}(v3,v5)")
lst = drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def test_modal(self):
data_drs = Drs.create_from_natural_language('alberto can dance')
expected_drs = Drs.create_from_predicates_string(
'{"tag": "MD", "word": "can"}(2), {"type": "MODAL"}(3,2), {"tag": "v"}(3)')
lst = data_drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 0
self.assertTrue(is_match)
def test_copula(self):
drs = Drs.create_from_natural_language('this is a test')
expected_drs = Drs.create_from_predicates_string(
"{'word': 'is', 'compound': 'is', 'tag': 'v', 'entity': ''}(v1), {'word': 'this', 'compound': 'this', 'tag': 'DT', 'entity': ''}(v0), {'word': 'test', 'compound': 'test', 'tag': 'n', 'entity': ''}(v3), {'type': 'AGENT'}(v1,v0), {'type': 'ATTR'}(v1,v3)")
lst = drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def test_creation_from_drt_with_preposition(self):
drs = Drs.create_from_predicates_string(
"{'word': 'ideas', 'entity': '', 'tag': 'n', 'compound': 'ideas'}(v0), {'word': 'Jim', 'entity': '', 'tag': 'n', 'compound': 'Jim'}(v2), {'type': 'of'}(v0,v2)")
expected_drs = Drs.create_from_predicates_string(
"{'word': 'ideas', 'entity': '', 'tag': 'n', 'compound': 'ideas'}(v0), {'word': 'Jim', 'entity': '', 'tag': 'n', 'compound': 'Jim'}(v2), {'type': 'of'}(v0,v2)")
lst = drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def test_compound_nouns_gender_guess(self):
text = "Jane Smith is an engineer"
drs = Drs.create_from_natural_language(text)
expected_drs = Drs.create_from_predicates_string(
"{'compound': 'Jane Smith', 'gender_guess': 'f'}(a)")
lst = drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def test_snippet_2(self):
"""
Mostly to check conjunction rules.
"""
text = "Jon is a carpenter and an engineer"
drs = Drs.create_from_natural_language(text)
expected_drs = Drs.create_from_predicates_string("""
{'word': 'is', 'tag': 'v', 'compound': 'is', 'entity': '', 'lemma': 'be', 'gender_guess': None, 'is_head_token': True, 'refers_to': None, 'negated': 'false'}(v1), {'word': 'Jon', 'tag': 'n', 'compound': 'Jon', 'entity': 'PERSON', 'lemma': 'Jon', 'gender_guess': 'm', 'is_head_token': False, 'refers_to': None, 'negated': 'false'}(v0), {'word': 'carpenter', 'tag': 'n', 'compound': 'carpenter', 'entity': '', 'lemma': 'carpenter', 'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false'}(v3), {'word': 'engineer', 'tag': 'n', 'compound': 'engineer', 'entity': '', 'lemma': 'engineer', 'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false'}(v6), {'type': 'AGENT'}(v1,v0), {'type': 'ATTR'}(v1,v6), {'type': 'ATTR'}(v1,v3), {'type': 'ATTR'}(v1,v6)
""")
lst = drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def test_relation_rules(self):
data_drs = Drs.create_from_natural_language('Jim works at Microsoft')
knowledge = Knowledge(metric)
knowledge.add_rules(open(os.path.join(_path, '../rules/generic_relations.rules')).read())
inference = ForwardInference(data_drs, knowledge)
end_drs = inference.compute()
expected_drs = Drs.create_from_predicates_string('{}(1), {"text": "WORKS_AT"}(1,2), {}(2)')
is_match = False
for drs in end_drs:
lst = drs[0].apply(DrsMatcher(expected_drs, metric))
if len(lst) > 0:
is_match = True
break
self.assertTrue(is_match)
def test_coreference_is_joined_in_graph(self):
text = "John is ginger. He is a carpenter. test. Jane is blond. She is a carpenter. "
discourse = Discourse(text)
expected_drs = Drs.create_from_predicates_string(
"{}(a), {}(b), {'type': 'REFERS_TO'}(a,b)")
lst = discourse._discourse.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def test_birth_date2(self):
sentence = 'John was born in 10 August 1582'
drs = Drs.create_from_natural_language(sentence)
fi = ForwardInference(drs, _knowledge)
drs_and_weight = fi.compute()
writer = RelationTripletsWriter()
lst = drs_and_weight[0][0].apply(writer)
expected_list = [('John', 'BIRTH_DAY', '10_August_1582')]
self.assertEqual(lst, expected_list)
def test_personal_pronouns(self):
sentence = 'I have a red dog'
drs = Drs.create_from_natural_language(sentence)
fi = ForwardInference(drs, _knowledge)
drs_and_weight = fi.compute()
writer = RelationTripletsWriter()
lst = drs_and_weight[0][0].apply(writer)
expected_list = [('I', 'OWN', 'dog')]
self.assertEqual(lst, expected_list)
def visit(self, g):
if not isinstance(g, Graph):
raise TypeError(
"DrsRule.visit_to_graph() needs an igraph.Graph as an argument"
)
for vertex in g.vs:
if vertex['word'] in self._words_without_entity:
vertex['entity'] = ''
return Drs(g)
def test_single_clause(self):
data_drs = Drs.create_from_natural_language('Jim works at Microsoft')
rule = """
MATCH "{PERSON}#1 works at {ORG}#2"
CREATE {}(1), {"type": "WORKS_AT"}(1,2), {}(2)
"""
knowledge = Knowledge(metric)
knowledge.add_rules(rule)
inference = ForwardInference(data_drs, knowledge)
end_drs = inference.compute()
expected_drs = Drs.create_from_predicates_string('{}(1), {"type": "WORKS_AT"}(1,2), {}(2)')
is_match = False
for drs in end_drs:
lst = drs[0].apply(DrsMatcher(expected_drs, metric))
if len(lst) > 0:
is_match = True
break
self.assertTrue(is_match)
def test_possesive_pronouns(self):
sentence = 'My dog is red'
drs = Drs.create_from_natural_language(sentence)
knowledge = Knowledge()
knowledge.add_rules(open(os.path.join(_path, '../rules/test.rules')).read())
fi = ForwardInference(drs, knowledge)
drs_and_weight = fi.compute()
writer = RelationTripletsWriter()
lst = drs_and_weight[0][0].apply(writer)
expected_list = [('me', 'OWN', 'dog')]
self.assertEqual(lst, expected_list)
def test_drt_graph(self):
sentence = 'John is tall'
drs = Drs.create_from_natural_language(sentence)
writer = DRTTripletsWriter()
triplets = drs.apply(writer)
expected_triplets = {'edges': [{'arrows': 'to', 'from': 'v1', 'label': 'AGENT', 'to': 'v0'},
{'arrows': 'to', 'from': 'v1', 'label': 'ADJECTIVE', 'to': 'v2'}],
'nodes': [{'id': 'v1', 'label': 'is'},
{'id': 'v0', 'label': 'John'},
{'id': 'v2', 'label': 'tall'}]}
self.assertEqual(triplets, expected_triplets)
def test_asimov_wiki(self):
text = open(os.path.join(_path, '../data/wiki_asimov.txt')).read()
discourse = Discourse(text)
extractor = Extractor(discourse, _knowledge)
triplets = extractor.extract()
expected_triplets = [('Isaac_Asimov_0|Asimov_0', 'JOB_TITLE', 'writer'),
('Isaac_Asimov_0|Asimov_0', 'OWNS', 'works'),
('Isaac_Asimov_0|Asimov_0', 'OWNS', 'books')]
self.assertTrue(triplets, expected_triplets)
expected_drs = Drs.create_from_predicates_string(
"{}(a), {'word': 'Boston_University'}(b), {'type': 'at'}(a,b)")
lst = discourse._discourse.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def _substitute_text_in_match_statement_with_graph(text,
substitution_triggers):
drs_cleaner = DrsNERCleaner(substitution_triggers)
p = re.compile('MATCH.*\"(.*)\"')
lst = p.findall(text)
if not lst:
p = re.compile('MATCH.*\'(.*)\'')
lst = p.findall(text)
for item in lst:
try:
drs = Discourse(item).connected_components[0]
except IndexError:
_logger.warning('Cannot use Discourse on %s' % item[:200])
drs = Drs.create_from_natural_language(item)
drs = drs.apply(drs_cleaner)
text = text.replace('"' + item + '"', str(drs))
return text
import os from pynsett.discourse import Discourse from pynsett.drt import Drs from pynsett.extractor import Extractor from pynsett.knowledge import Knowledge _path = os.path.dirname(__file__) text = "John Smith is not blond" drs = Drs.create_from_natural_language(text) drs.plot() print(drs)
_path = os.path.dirname(__file__)
#sentence = "John has a house"
#sentence = "Centuries later John wrote to his brother Theo"
#sentence = "Hans was born in 1582 or 1583 in Antwerp, then in the Spanish Netherlands, as the son of cloth merchant Franchois Fransz Hals van Mechelen (c.1542–1610) and his second wife Adriaentje van Geertenryck.[2] Like many, Hals' parents fled during[citation needed] the Fall of Antwerp (1584–1585) from the south to Haarlem in the new Dutch Republic in the north, where he lived for the remainder of his life. Hals studied under Flemish émigré Karel van Mander,[2][3] whose Mannerist influence, however, is barely noticeable in Hals' work."
#sentence = 'It is not known whether Hals ever painted landscapes'
#sentence = 'John drove home where he has a cat.'
#sentence = 'His dog was red'
#sentence = 'My own dog is red'
#sentence = 'Jane has a bicycle'
#sentence = 'Jane Smith is an engineer'
#sentence = 'Jane works as an engineer'
#sentence = 'Jane works for Google'
sentence = "John was born in 1582 or 1583 in Antwerp"
drs = Drs.create_from_natural_language(sentence)
print(drs)
anaphora = SingleSentenceAnaphoraVisitor()
drs.apply(anaphora)
head_token_visitor = HeadTokenVisitor(1)
drs.apply(head_token_visitor)
print('---')
print(drs)
knowledge = Knowledge()
knowledge.add_rules(open(os.path.join(_path, '../rules/test.rules')).read())
#knowledge.add_rules(open(os.path.join(_path, '../rules/generic_relations.rules')).read())
def test_if_rule(self):
data_drs = Drs.create_from_natural_language('If I breathe I am alive')
expected_drs = Drs.create_from_predicates_string('{}(a), {"type": "CONDITION"}(a,b), {}(b)')
lst = data_drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 0
self.assertTrue(is_match)
def test_snippet_1(self):
"""
Mostly to check conjunction rules.
"""
text = "Asimov also wrote mysteries and fantasy, as well as much nonfiction. Most of his popular science books explain concepts in a historical way, going as far back as possible to a time when the science in question was at its simplest stage. Examples include Guide to Science, the three-volume set Understanding Physics, and Asimov's Chronology of Science and Discovery. He wrote on numerous other scientific and non-scientific topics, such as chemistry, astronomy, mathematics, history, biblical exegesis, and literary criticism."
drs = Drs.create_from_natural_language(text)
expected_drs = Drs.create_from_predicates_string("""
{'word': 'wrote', 'tag': 'v', 'compound': 'wrote', 'entity': '', 'lemma': 'write', 'gender_guess': None,
'is_head_token': True, 'refers_to': None, 'negated': 'false', 'type': None}(v2),
{'word': 'Asimov', 'tag': 'n', 'compound': 'Asimov', 'entity': 'PERSON', 'lemma': 'Asimov',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v0),
{'word': 'also', 'tag': 'RB', 'compound': 'also', 'entity': '', 'lemma': 'also', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v1),
{'word': 'mysteries', 'tag': 'n', 'compound': 'mysteries', 'entity': '', 'lemma': 'mystery',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v3),
{'word': 'fantasy', 'tag': 'n', 'compound': 'fantasy', 'entity': '', 'lemma': 'fantasy',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v5),
{'word': 'nonfiction', 'tag': 'n', 'compound': 'nonfiction', 'entity': '', 'lemma': 'nonfiction',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v11),
{'word': 'as', 'tag': 'RB', 'compound': 'as', 'entity': '', 'lemma': 'as', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v7),
{'word': 'well', 'tag': 'RB', 'compound': 'well', 'entity': '', 'lemma': 'well', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v8),
{'word': 'much', 'tag': 'j', 'compound': 'much', 'entity': '', 'lemma': 'much', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v10),
{'word': 'Most', 'tag': 'j', 'compound': 'Most', 'entity': '', 'lemma': 'Most', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v13),
{'word': 'books', 'tag': 'n', 'compound': 'books', 'entity': '', 'lemma': 'book', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v18),
{'word': 'he', 'tag': 'PRP$', 'compound': 'he', 'entity': '', 'lemma': 'he', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v15),
{'word': 'popular', 'tag': 'j', 'compound': 'popular', 'entity': '', 'lemma': 'popular',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v16),
{'word': 'science', 'tag': 'n', 'compound': 'science', 'entity': '', 'lemma': 'science',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v17),
{'word': 'explain', 'tag': 'v', 'compound': 'explain', 'entity': '', 'lemma': 'explain',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v19),
{'word': 'concepts', 'tag': 'n', 'compound': 'concepts', 'entity': '', 'lemma': 'concept',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v20),
{'word': 'going', 'tag': 'v', 'compound': 'going', 'entity': '', 'lemma': 'go', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v26),
{'word': 'way', 'tag': 'n', 'compound': 'way', 'entity': '', 'lemma': 'way', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v24),
{'word': 'historical', 'tag': 'j', 'compound': 'historical', 'entity': '', 'lemma': 'historical',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v23),
{'word': 'back', 'tag': 'RB', 'compound': 'back', 'entity': '', 'lemma': 'back', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v29),
{'word': 'to', 'tag': 'IN', 'compound': 'to', 'entity': '', 'lemma': 'to', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'to'}(v32),
{'word': 'far', 'tag': 'RB', 'compound': 'far', 'entity': '', 'lemma': 'far', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v28),
{'word': 'as', 'tag': 'RB', 'compound': 'as', 'entity': '', 'lemma': 'as', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v27),
{'word': 'as', 'tag': 'IN', 'compound': 'as', 'entity': '', 'lemma': 'as', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'as'}(v30),
{'word': 'possible', 'tag': 'j', 'compound': 'possible', 'entity': '', 'lemma': 'possible',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v31),
{'word': 'time', 'tag': 'n', 'compound': 'time', 'entity': '', 'lemma': 'time', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v34),
{'word': 'was', 'tag': 'v', 'compound': 'was', 'entity': '', 'lemma': 'be', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v40),
{'word': 'science', 'tag': 'n', 'compound': 'science', 'entity': '', 'lemma': 'science',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v37),
{'word': 'in', 'tag': 'IN', 'compound': 'in', 'entity': '', 'lemma': 'in', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'in'}(v38),
{'word': 'question', 'tag': 'n', 'compound': 'question', 'entity': '', 'lemma': 'question',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v39),
{'word': 'when', 'tag': 'WRB', 'compound': 'when', 'entity': '', 'lemma': 'when', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v35),
{'word': 'at', 'tag': 'IN', 'compound': 'at', 'entity': '', 'lemma': 'at', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'at'}(v41),
{'word': 'stage', 'tag': 'n', 'compound': 'stage', 'entity': '', 'lemma': 'stage', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v44),
{'word': 'its', 'tag': 'PRP$', 'compound': 'its', 'entity': '', 'lemma': 'its', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v42),
{'word': 'simplest', 'tag': 'j', 'compound': 'simplest', 'entity': '', 'lemma': 'simple',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v43),
{'word': 'include', 'tag': 'v', 'compound': 'include', 'entity': '', 'lemma': 'include',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v47),
{'word': 'Examples', 'tag': 'n', 'compound': 'Examples', 'entity': '', 'lemma': 'example',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v46),
{'word': 'Guide', 'tag': 'n', 'compound': 'Guide', 'entity': '', 'lemma': 'Guide', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v48),
{'word': '.', 'tag': '.', 'compound': '.', 'entity': '', 'lemma': '.', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v68),
{'word': 'to', 'tag': 'IN', 'compound': 'to', 'entity': '', 'lemma': 'to', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v49),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'and'}(v51),
{'word': 'set', 'tag': 'v', 'compound': 'set', 'entity': '', 'lemma': 'set', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v56),
{'word': 'Science', 'tag': 'n', 'compound': 'Science', 'entity': '', 'lemma': 'Science',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v50),
{'word': 'volume', 'tag': 'n', 'compound': 'volume', 'entity': '', 'lemma': 'volume', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v55),
{'word': 'three', 'tag': 'CD', 'compound': 'three', 'entity': 'CARDINAL', 'lemma': 'three',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v53),
{'word': '-', 'tag': 'HYPH', 'compound': '-', 'entity': '', 'lemma': '-', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v54),
{'word': 'Physics', 'tag': 'n', 'compound': 'Understanding_Physics', 'entity': 'ORG', 'lemma': 'Physics',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v58),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v59),
{'word': 'and', 'tag': 'CC', 'compound': 'and', 'entity': '', 'lemma': 'and', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'and'}(v60),
{'word': 'Chronology', 'tag': 'n', 'compound': 'Chronology', 'entity': 'WORK_OF_ART', 'lemma': 'Chronology',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v63),
{'word': 'Asimov', 'tag': 'n', 'compound': 'Asimov', 'entity': 'PERSON', 'lemma': 'Asimov',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v61),
{'word': 'of', 'tag': 'IN', 'compound': 'of', 'entity': 'WORK_OF_ART', 'lemma': 'of', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v64),
{'word': 'Science', 'tag': 'n', 'compound': 'Science', 'entity': 'WORK_OF_ART', 'lemma': 'Science',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v65),
{'word': 'and', 'tag': 'CC', 'compound': 'and', 'entity': 'WORK_OF_ART', 'lemma': 'and',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'and'}(v66),
{'word': 'Discovery', 'tag': 'n', 'compound': 'Discovery', 'entity': 'WORK_OF_ART', 'lemma': 'Discovery',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v67),
{'word': 'wrote', 'tag': 'v', 'compound': 'wrote', 'entity': '', 'lemma': 'write', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v70),
{'word': 'He', 'tag': 'PRP', 'compound': 'He', 'entity': 'PERSON', 'lemma': 'he', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v69),
{'word': 'on', 'tag': 'IN', 'compound': 'on', 'entity': '', 'lemma': 'on', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v71),
{'word': '.', 'tag': '.', 'compound': '.', 'entity': '', 'lemma': '.', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v97),
{'word': 'topics', 'tag': 'n', 'compound': 'topics', 'entity': '', 'lemma': 'topic', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v79),
{'word': 'scientific', 'tag': 'j', 'compound': 'scientific', 'entity': '', 'lemma': 'scientific',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v74),
{'word': '-', 'tag': 'j', 'compound': '-', 'entity': '', 'lemma': '-', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v77),
{'word': 'non', 'tag': 'j', 'compound': 'non', 'entity': '', 'lemma': 'non', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v76),
{'word': 'scientific', 'tag': 'j', 'compound': 'scientific', 'entity': '', 'lemma': 'scientific',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v78),
{'word': 'numerous', 'tag': 'j', 'compound': 'numerous', 'entity': '', 'lemma': 'numerous',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v72),
{'word': 'other', 'tag': 'j', 'compound': 'other', 'entity': '', 'lemma': 'other', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v73),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v80),
{'word': 'as', 'tag': 'IN', 'compound': 'as', 'entity': '', 'lemma': 'as', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'as'}(v82),
{'word': 'such', 'tag': 'j', 'compound': 'such', 'entity': '', 'lemma': 'such', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v81),
{'word': 'chemistry', 'tag': 'n', 'compound': 'chemistry', 'entity': '', 'lemma': 'chemistry',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v83),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': 'and'}(v84),
{'word': 'astronomy', 'tag': 'n', 'compound': 'astronomy', 'entity': '', 'lemma': 'astronomy',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v85),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v86),
{'word': 'mathematics', 'tag': 'n', 'compound': 'mathematics', 'entity': '', 'lemma': 'mathematic',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v87),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v88),
{'word': 'history', 'tag': 'n', 'compound': 'history', 'entity': '', 'lemma': 'history',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v89),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v90),
{'word': 'exegesis', 'tag': 'n', 'compound': 'exegesis', 'entity': '', 'lemma': 'exegesis',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v92),
{'word': 'biblical', 'tag': 'j', 'compound': 'biblical', 'entity': '', 'lemma': 'biblical',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v91),
{'word': ',', 'tag': ',', 'compound': ',', 'entity': '', 'lemma': ',', 'gender_guess': None,
'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v93),
{'word': 'criticism', 'tag': 'n', 'compound': 'criticism', 'entity': '', 'lemma': 'criticism',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v96),
{'word': 'literary', 'tag': 'j', 'compound': 'literary', 'entity': '', 'lemma': 'literary',
'gender_guess': None, 'is_head_token': False, 'refers_to': None, 'negated': 'false', 'type': None}(v95),
{'type': 'AMOD'}(v24, v23), {'type': 'ADVMOD'}(v26, v29), {'type': 'ADVMOD'}(v28, v27),
{'type': 'ADVMOD'}(v29, v28), {'type': 'NSUBJ'}(v40, v37), {'type': 'POSS'}(v44, v42),
{'type': 'AMOD'}(v44, v43), {'type': 'NSUBJ'}(v47, v46), {'type': 'DOBJ'}(v47, v48),
{'type': 'PUNCT'}(v47, v68), {'type': 'PREP'}(v48, v49), {'type': 'POBJ'}(v49, v50),
{'type': 'PUNCT'}(v55, v54), {'type': 'NPADVMOD'}(v56, v55), {'type': 'DOBJ'}(v56, v58),
{'type': 'PUNCT'}(v56, v59), {'type': 'POSS'}(v63, v61), {'type': 'PREP'}(v63, v64),
{'type': 'POBJ'}(v64, v65), {'type': 'NSUBJ'}(v70, v69), {'type': 'PREP'}(v70, v71),
{'type': 'PUNCT'}(v70, v97), {'type': 'POBJ'}(v71, v79), {'type': 'SUBTOK'}(v77, v76),
{'type': 'SUBTOK'}(v78, v77), {'type': 'AMOD'}(v79, v72), {'type': 'AMOD'}(v79, v73),
{'type': 'AMOD'}(v79, v74), {'type': 'AMOD'}(v79, v78), {'type': 'PUNCT'}(v79, v80),
{'type': 'POBJ'}(v82, v83), {'type': 'PUNCT'}(v85, v86), {'type': 'CONJ'}(v85, v87),
{'type': 'PUNCT'}(v87, v88), {'type': 'CONJ'}(v87, v89), {'type': 'PUNCT'}(v89, v90),
{'type': 'CONJ'}(v89, v92), {'type': 'AMOD'}(v92, v91), {'type': 'PUNCT'}(v92, v93),
{'type': 'CONJ'}(v92, v96), {'type': 'AMOD'}(v96, v95), {'type': 'AGENT'}(v2, v0),
{'type': 'ADVOCATIVE_CLAUSE'}(v19, v26), {'type': 'when'}(v34, v40), {'type': 'of'}(v13, v18),
{'type': 'AGENT'}(v19, v13), {'type': 'PATIENT'}(v19, v20), {'type': 'in'}(v19, v24),
{'type': 'NUMBER'}(v55, v53), {'type': 'OWNS'}(v61, v63), {'type': 'OWNS'}(v15, v18),
{'type': 'PATIENT'}(v2, v5), {'type': 'and'}(v56, v63), {'type': 'and'}(v48, v56),
{'type': 'and'}(v65, v67), {'type': 'and'}(v83, v85), {'type': 'in'}(v37, v39), {'type': 'to'}(v26, v34),
{'type': 'as'}(v29, v31), {'type': 'at'}(v40, v44), {'type': 'as'}(v79, v81), {'type': 'of'}(v18, v17),
{'type': 'ADJECTIVE'}(v11, v10), {'type': 'ADVERB'}(v2, v1), {'type': 'ADJECTIVE'}(v18, v16),
{'type': 'as'}(v2, v3), {'type': 'as'}(v2, v5)""")
lst = drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 1
self.assertTrue(is_match)
def test_entity_parsing(self):
data_drs = Drs.create_from_natural_language('{PERSON} is in {GPE}')
expected_drs = Drs.create_from_natural_language('John is in London')
lst = data_drs.apply(DrsMatcher(expected_drs, metric))
is_match = len(lst) > 0
self.assertTrue(is_match)
def test_negation_matches(self):
drs = Drs.create_from_natural_language('John Smith is not blond')
expected_drs = Drs.create_from_natural_language('John Smith is not blond')
lst = drs.apply(DrsMatcher(expected_drs, metric))
is_not_match = len(lst) > 0
self.assertTrue(is_not_match)
def test_sub_isomorphism(self):
large_drs = Drs.create_from_natural_language('The ideas#1 of Jim#2 are silly')
small_drs = Drs.create_from_natural_language('ideas#3 of Jim#4')
lst = large_drs.apply(DrsMatcher(small_drs, metric))
is_match = len(lst) > 0
self.assertTrue(is_match)
