def get_candidates(self, text_order, candidate_order, mention, index_sent):
""" Gets the candidates ordered in a for the sieve check.
:param text_order: The list of sentences that contain the list of mentions that form the text.
:param candidate_order: The list of sentences that contain the list of mentions that form the text in bts order.
:param mention: The mention whose candidates whe need.
:param index_sent: The index of the current sentence.
@rtype : list
:return: A list of ordered candidates.
"""
mention_index = [c[ID] for c in candidate_order[index_sent]
].index(mention["id"])
if len(candidate_order[index_sent][mention_index]["entity"]
[1]) == 1 and self.is_pronoun(mention):
self.logger.debug("ORDERING: pronoun order")
sentence_candidates = self.pronoun_order(
candidate_order[index_sent][:mention_index], mention)
other_candidates = [
m for s in reversed(text_order[:index_sent]) for m in s
]
if pronouns.relative(mention[FORM].lower()):
self.logger.debug("ORDERING: Relative pronoun order")
sentence_candidates.reverse()
return sentence_candidates + other_candidates
else:
return super(PronounSieve,
self).get_candidates(text_order, candidate_order,
mention, index_sent)
def is_relative_pronoun(graph_builder, first_constituent, second_constituent):
""" Check if tho constituents are in relative pronoun construction.
Also mark they.
:param graph_builder: The graph manager.
:param first_constituent:
:param second_constituent:
:return: Boolean
"""
# NP < (NP=m1 $.. (SBAR < (WHNP < WP|WDT=m2)))
if not graph_builder.same_sentence(first_constituent, second_constituent):
return False
if not pronouns.relative(second_constituent[FORM].lower()):
return False
if first_constituent[SPAN] > second_constituent[SPAN]:
return False
enclosing_np = graph_builder.get_syntactic_parent(first_constituent)
upper = graph_builder.get_syntactic_parent(second_constituent)
while upper and (upper[graph_builder.node_type] !=
graph_builder.root_type):
if graph_builder.is_inside(upper[SPAN], enclosing_np[SPAN]):
upper = graph_builder.get_syntactic_parent(upper)
elif upper[ID] == enclosing_np[ID]:
# TODO check path element
return True
else:
return False
return False
def are_coreferent(self, entity, mention, candidate_entity, candidate):
"""A pronoun is coreferent with a candidate?
:param mention: The selected mention to represent the entity.
:param entity: The entity that mention is part.
:param candidate: The candidate that may corefer the entity.
:param candidate_entity: The entity that candidate is part of it.
:return: True or false
"""
if pronouns.relative(candidate[FORM]):
return False
if candidate.get(PLEONASTIC, False):
return False
if self.FORBID_POSSESSIVES \
and self.is_possessive(mention):
return False
if self.RESTRICT_POSSESSIVES_WITH_POSSESSIONS \
and self.is_pronoun(mention) and self.is_possessive(mention)\
and self.starts_with_possessive(candidate)\
and not self.is_pronoun(candidate):
return False
if self.RESTRICT_ADJACENT and mention[SPAN][
0] == candidate[SPAN][1] + 1:
return False
return super(SpanishPronounMatch,
self).are_coreferent(entity, mention, candidate_entity,
candidate)
def extract_and_mark(self, mention):
""" Determine the type of the mention. Also check some mention related
features.
:param mention: The mention to be classified.
"""
words = self.graph_builder.get_words(mention)
head = self.graph_builder.get_head_word(mention)
head_pos = head[POS]
head_form = head[FORM].lower()
head_word_ner = head.get(HEAD_OF_NER)
first_form = words[0][FORM].lower()
if pronouns.relative(first_form) and len(words) == 1:
mention[RELATIVE_PRONOUN] = True
else:
mention[RELATIVE_PRONOUN] = False
if determiners.indefinite_articles(first_form):
mention[STARTED_BY_INDEFINITE_ARTICLE] = True
else:
mention[STARTED_BY_INDEFINITE_ARTICLE] = False
if pronouns.indefinite(first_form):
mention[STARTED_BY_INDEFINITE_PRONOUN] = True
else:
mention[STARTED_BY_INDEFINITE_PRONOUN] = False
# Enumeration mention
if rules.is_enumeration(self.graph_builder, mention):
self._set_mention_type(mention, ENUMERATION_MENTION)
# Pronoun mention
elif (len(words) == 1 and pos_tags.pronoun(head_pos)) or\
(len(words) == 1 and (pronouns.all(head_form) or pronouns.relative(head_form)) and
# not ner_tags.mention_ner(head_word_ner)):
True):
self._set_mention_type(mention, PRONOUN_MENTION)
# Proper Mention
elif pos_tags.proper_noun(head_pos): # or ner_tags.all(head_word_ner):
self._set_mention_type(mention, PROPER_MENTION)
# In other case is nominal
else:
self._set_mention_type(mention, NOMINAL_MENTION)
def validate(self, mention, entity):
""" Only pronouns can be used for this sieve
:param mention: The mention to check.
:param entity: The entity of the mention.
"""
if not super(SpanishPronounMatch, self).validate(mention, entity):
return False
if pronouns.relative(mention[FORM]):
return False
if mention[PLEONASTIC]:
return False
return True
def is_appositive_construction_child(graph_builder, constituent):
""" Check if the mention is in a appositive construction.
"NP=m1 < (NP=m2 $.. (/,/ $.. NP=m3))";
"NP=m1 < (NP=m2 $.. (/,/ $.. (SBAR < (WHNP < WP|WDT=m3))))";
"/^NP(?:-TMP|-ADV)?$/=m1 < (NP=m2 $- /^,$/ $-- NP=m3 !$ CC|CONJP)";
"/^NP(?:-TMP|-ADV)?$/=m1 <
(PRN=m2 < (NP < /^NNS?|CD$/ $-- /^-LRB-$/ $+ /^-RRB-$/))";
:param graph_builder: The graphBuilder
:param constituent: The mention to check
"""
constituent = constituent.get("constituent", constituent)
# mention is inside a NP
# TODO Improve the precision
parent = graph_builder.get_syntactic_parent(constituent)
if not constituent_tags.noun_phrase(parent[TAG]):
return False
siblings = graph_builder.get_syntactic_sibling(constituent)
# Check if
while siblings:
actual = siblings.pop(0)
if actual == constituent:
break
else:
return False
while siblings:
actual = siblings.pop(0)
if actual[FORM] == ",":
break
else:
return False
while siblings:
actual = siblings.pop(0)
if constituent_tags.noun_phrase(actual.get(TAG)):
return parent
if pronouns.relative(graph_builder.get_words(actual)[0].get("form")):
return parent
return False
def process_graph(self):
from corefgraph.multisieve.features.constants import MENTION
""" Prepare the graph for output.
"""
self.meta[self.graph_builder.doc_type] = self.graph_builder.get_doc_type()
from corefgraph.resources.tagset import pos_tags
from corefgraph.resources.dictionaries import pronouns
self.meta["sentences"] = {
'words_histogram': [len(self.graph_builder.get_words(sentence))
for sentence in self.graph_builder.get_all_sentences()],
'pronouns_histogram': [len([word for word in self.graph_builder.get_words(sentence) if(pos_tags.pronoun(word[POS]) or pronouns.all(word[FORM]) or pronouns.relative(word[FORM]))])
for sentence in self.graph_builder.get_all_sentences()],
'named_entities_histogram': [len(self.graph_builder.get_sentence_named_entities(sentence))
for sentence in self.graph_builder.get_all_sentences()],
'mentions_histogram': [len(self.graph_builder.get_sentence_gold_mentions(sentence))
for sentence in self.graph_builder.get_all_sentences()]
}
self.meta["features"] = {
'counters': defaultdict(Counter),
'mentions': defaultdict(dict)}
for index, sentence in enumerate(self.coreference_processor.mentions_textual_order):
self.logger.debug("Featuring Sentence %d", index)
sentence_mentions = []
# self.meta["sentences"].append(sentence_mentions)
for mention in sentence:
# Store mentions id in the meta
sentence_mentions.append(mention[ID])
self.feature_extractor.characterize_mention(mention)
# Resolve the coreference
self.logger.debug("Resolve Coreference...")
self.coreference_processor.resolve_text()
self.meta["overall"] = {
'words': Counter([word[POS] for word in self.graph_builder.get_all_words()]),
'namedEntities': Counter([ne[NER] for ne in self.graph_builder.get_all_named_entities()]),
'constituents': Counter([constituent[TAG] for constituent in self.graph_builder.get_all_constituents()]),
'mentions': Counter([mention.get(MENTION) for mention in self.graph_builder.get_all_gold_mentions()]),
'mentions_size': [len(self.graph_builder.get_words(mention)) for mention in self.graph_builder.get_all_gold_mentions()],
'mentions_deep': [mention.get(CONSTITUENT, {DEEP: -1})[DEEP] for mention in self.graph_builder.get_all_gold_mentions()],
'mentions_per_entity': Counter([mention[GOLD_ENTITY] for mention in self.graph_builder.get_all_gold_mentions()]).values()
}