def test_gender(self):
self.assertEqual(
"MALE",
mention_property_computer.compute_gender(
{"tokens": ["him"], "pos": ["PRP"], "type": "PRO",
"citation_form": "he", "head_index": 0}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender(
{"tokens": ["its"], "pos": ["PRP$"], "type": "PRO",
"citation_form": "it", "head_index": 0}))
self.assertEqual(
"FEMALE",
mention_property_computer.compute_gender(
{"tokens": ["Mrs.", "Robinson"], "pos": ["NNP", "NNP"],
"type": "NAM", "head_index": 1}))
self.assertEqual(
"MALE",
mention_property_computer.compute_gender(
{"tokens": ["Mr.", "FooBar"], "pos": ["NNP", "NNP"],
"type": "NAM", "head_index": 1}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender(
{"tokens": ["an", "arrow"], "head": ["arrow"],
"pos": ["DT", "NN"],"type": "NOM", "ner": ["-", "-"],
"head_index": 1}))
self.assertEqual(
"FEMALE",
mention_property_computer.compute_gender(
{"tokens": ["the", "girl"], "head": ["girl"],
"pos": ["DT", "NN"],"type": "NOM", "ner": ["-", "-"],
"head_index": 1}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender(
{"tokens": ["the", "shooting"], "head": ["shooting"],
"pos": ["DT", "NN"],"type": "NOM", "ner": ["-", "-"],
"head_index": 1}))
self.assertEqual(
"MALE",
mention_property_computer.compute_gender(
{"tokens": ["the", "groom"], "head": ["groom"],
"pos": ["DT", "NN"],"type": "NOM", "ner": ["-", "-"],
"head_index": 1}))
self.assertEqual(
"PLURAL",
mention_property_computer.compute_gender(
{"tokens": ["the", "guys"], "head": ["guys"],
"pos": ["DT", "NNS"],"type": "NOM", "ner": ["-", "-"],
"head_index": 1}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender(
{"tokens": ["the", "Mona", "Lisa"], "head": ["Mona", "Lisa"],
"pos": ["DT", "NNP", "NNP"],"type": "NAM",
"ner": ["-", "WORK_OF_ART", "WORK_OF_ART"], "head_index": 2}))
def from_document(span, document, first_in_gold_entity=False):
"""
Create a mention from a span in a document.
All attributes of the mention are computed from the linguistic
information found in the document. For information about the
attributes, see the class documentation.
Args:
document (CoNLLDocument): The document the mention belongs to.
span (Span): The span of the mention in the document.
Returns:
Mention: A mention extracted from the input span in the input
document.
"""
i, sentence_span = document.get_sentence_id_and_span(span)
attributes = {
"tokens": document.tokens[span.begin:span.end + 1],
"pos": document.pos[span.begin:span.end + 1],
"ner": document.ner[span.begin:span.end + 1],
"sentence_id": i,
"parse_tree": mention_property_computer.get_relevant_subtree(
span, document),
"speaker": document.speakers[span.begin],
"antecedent": None,
"set_id": None,
"first_in_gold_entity": first_in_gold_entity
}
if span in document.coref:
attributes["annotated_set_id"] = document.coref[span]
else:
attributes["annotated_set_id"] = None
attributes["is_apposition"] = \
mention_property_computer.is_apposition(attributes)
attributes["grammatical_function"] = \
mention_property_computer.get_grammatical_function(attributes)
(head, in_mention_span, head_index) = \
mention_property_computer.compute_head_information(attributes)
attributes["head"] = head
attributes["head_span"] = spans.Span(
span.begin + in_mention_span.begin,
span.begin + in_mention_span.end
)
attributes["head_index"] = head_index
attributes["type"] = mention_property_computer.get_type(attributes)
attributes["fine_type"] = mention_property_computer.get_fine_type(
attributes)
if attributes["type"] == "PRO":
attributes["citation_form"] = \
mention_property_computer.get_citation_form(
attributes)
attributes["number"] = \
mention_property_computer.compute_number(attributes)
attributes["gender"] = \
mention_property_computer.compute_gender(attributes)
attributes["semantic_class"] = \
mention_property_computer.compute_semantic_class(attributes)
attributes["head_as_lowercase_string"] = " ".join(attributes[
"head"]).lower()
attributes["tokens_as_lowercase_string"] = " ".join(attributes[
"tokens"]).lower()
dep_tree = document.dep[i]
index = span.begin + head_index - sentence_span.begin
governor_id = dep_tree[index].head - 1
if governor_id == -1:
attributes["governor"] = "NONE"
else:
attributes["governor"] = dep_tree[governor_id].form.lower()
attributes["ancestry"] = Mention._get_ancestry(dep_tree, index)
attributes["deprel"] = dep_tree[index].deprel
return Mention(document, span, attributes)
def test_gender(self):
self.assertEqual(
"MALE",
mention_property_computer.compute_gender({
"tokens": ["him"],
"pos": ["PRP"],
"type": "PRO",
"citation_form": "he",
"head_index": 0
}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender({
"tokens": ["its"],
"pos": ["PRP$"],
"type": "PRO",
"citation_form": "it",
"head_index": 0
}))
self.assertEqual(
"FEMALE",
mention_property_computer.compute_gender({
"tokens": ["Mrs.", "Robinson"],
"pos": ["NNP", "NNP"],
"type":
"NAM",
"head_index":
1
}))
self.assertEqual(
"MALE",
mention_property_computer.compute_gender({
"tokens": ["Mr.", "FooBar"],
"pos": ["NNP", "NNP"],
"type":
"NAM",
"head_index":
1
}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender({
"tokens": ["an", "arrow"],
"head": ["arrow"],
"pos": ["DT", "NN"],
"type": "NOM",
"ner": ["-", "-"],
"head_index": 1
}))
self.assertEqual(
"FEMALE",
mention_property_computer.compute_gender({
"tokens": ["the", "girl"],
"head": ["girl"],
"pos": ["DT", "NN"],
"type": "NOM",
"ner": ["-", "-"],
"head_index": 1
}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender({
"tokens": ["the", "shooting"],
"head": ["shooting"],
"pos": ["DT", "NN"],
"type":
"NOM",
"ner": ["-", "-"],
"head_index":
1
}))
self.assertEqual(
"MALE",
mention_property_computer.compute_gender({
"tokens": ["the", "groom"],
"head": ["groom"],
"pos": ["DT", "NN"],
"type": "NOM",
"ner": ["-", "-"],
"head_index": 1
}))
self.assertEqual(
"PLURAL",
mention_property_computer.compute_gender({
"tokens": ["the", "guys"],
"head": ["guys"],
"pos": ["DT", "NNS"],
"type": "NOM",
"ner": ["-", "-"],
"head_index": 1
}))
self.assertEqual(
"NEUTRAL",
mention_property_computer.compute_gender({
"tokens": ["the", "Mona", "Lisa"],
"head": ["Mona", "Lisa"],
"pos": ["DT", "NNP", "NNP"],
"type":
"NAM",
"ner": ["-", "WORK_OF_ART", "WORK_OF_ART"],
"head_index":
2
}))