def is_both_data_or_time(mention1: MentionDataLight,
mention2: MentionDataLight) -> bool:
"""
check if both phrases refers to time or date
Returns:
bool
"""
mention1_ner = mention1.mention_ner
mention2_ner = mention2.mention_ner
if mention1_ner is None:
_, _, _, mention1_ner = StringUtils.find_head_lemma_pos_ner(
mention1.tokens_str)
if mention2_ner is None:
_, _, _, mention2_ner = StringUtils.find_head_lemma_pos_ner(
mention2.tokens_str)
is1_time_or_data = 'DATE' in mention1_ner or 'TIME' in mention1_ner
is2_time_or_data = 'DATE' in mention2_ner or 'TIME' in mention2_ner
result = False
if is1_time_or_data and is2_time_or_data:
result = True
return result
def __init__(
self,
tokens_str: str,
mention_context: str = None,
mention_head: str = None,
mention_head_lemma: str = None,
mention_pos: str = None,
mention_ner: str = None,
):
"""
Object represent a mention with only text values
Args:
tokens_str: str the tokens combine text (join with space)
mention_head: str
mention_head_lemma: str
"""
self.tokens_str = tokens_str
self.mention_context = mention_context
if not mention_head and not mention_head_lemma:
(
self.mention_head,
self.mention_head_lemma,
self.mention_head_pos,
self.mention_ner,
) = StringUtils.find_head_lemma_pos_ner(str(tokens_str))
else:
self.mention_head = mention_head
self.mention_head_lemma = mention_head_lemma
self.mention_head_pos = mention_pos
self.mention_ner = mention_ner
def read_json_mention_data_line(mention_line: str):
"""
Args:
mention_line: a Json representation of a single mention
Returns:
MentionData object
"""
mention_data = None
try:
topic_id = None
coref_chain = None
doc_id = None
sent_id = None
tokens_numbers = None
score = -1
mention_type = None
predicted_coref_chain = None
mention_context = None
is_continue = False
is_singleton = False
mention_pos = None
mention_ner = None
mention_text = mention_line['tokens_str']
if 'topic_id' in mention_line:
topic_id = mention_line['topic_id']
if 'coref_chain' in mention_line:
coref_chain = mention_line['coref_chain']
if 'doc_id' in mention_line:
doc_id = mention_line['doc_id']
if '.xml' not in doc_id:
doc_id = doc_id + '.xml'
if 'sent_id' in mention_line:
sent_id = mention_line['sent_id']
if 'tokens_number' in mention_line:
tokens_numbers = mention_line['tokens_number']
if 'mention_context' in mention_line:
mention_context = mention_line['mention_context']
if 'mention_head' in mention_line and 'mention_head_lemma' in mention_line:
mention_head = mention_line['mention_head']
mention_head_lemma = mention_line['mention_head_lemma']
if 'mention_head_pos' in mention_line:
mention_pos = mention_line['mention_head_pos']
if 'mention_ner' in mention_line:
mention_ner = mention_line['mention_ner']
else:
mention_head, mention_head_lemma, mention_pos, \
mention_ner = StringUtils.find_head_lemma_pos_ner(str(mention_text))
if 'mention_type' in mention_line:
mention_type = mention_line['mention_type']
if 'score' in mention_line:
score = mention_line['score']
if 'is_continuous' in mention_line:
is_continue = mention_line['is_continuous']
if 'is_singleton' in mention_line:
is_singleton = mention_line['is_singleton']
if 'predicted_coref_chain' in mention_line:
predicted_coref_chain = mention_line['predicted_coref_chain']
mention_data = MentionData(
topic_id, doc_id, sent_id, tokens_numbers, mention_text,
mention_context, mention_head, mention_head_lemma, coref_chain,
mention_type, is_continue, is_singleton, score,
predicted_coref_chain, mention_pos, mention_ner)
except Exception:
print('Unexpected error:', sys.exc_info()[0])
raise Exception('failed reading json line-' + str(mention_line))
return mention_data
def read_json_mention_data_line(mention_line: str):
"""
Args:
mention_line: a Json representation of a single mention
Returns:
MentionData object
"""
# pylint: disable=too-many-branches
try:
topic_id = None
coref_chain = None
doc_id = None
sent_id = None
tokens_numbers = None
score = -1
mention_type = None
predicted_coref_chain = None
mention_context = None
is_continue = False
is_singleton = False
mention_pos = None
mention_ner = None
mention_index = -1
mention_text = mention_line["tokens_str"]
if "topic_id" in mention_line:
topic_id = mention_line["topic_id"]
if "coref_chain" in mention_line:
coref_chain = mention_line["coref_chain"]
if "doc_id" in mention_line:
doc_id = mention_line["doc_id"]
if ".xml" not in doc_id:
doc_id = doc_id + ".xml"
if "sent_id" in mention_line:
sent_id = mention_line["sent_id"]
if "tokens_number" in mention_line:
tokens_numbers = mention_line["tokens_number"]
if "mention_context" in mention_line:
mention_context = mention_line["mention_context"]
if "mention_head" in mention_line and "mention_head_lemma" in mention_line:
mention_head = mention_line["mention_head"]
mention_head_lemma = mention_line["mention_head_lemma"]
if "mention_head_pos" in mention_line:
mention_pos = mention_line["mention_head_pos"]
if "mention_ner" in mention_line:
mention_ner = mention_line["mention_ner"]
else:
(
mention_head,
mention_head_lemma,
mention_pos,
mention_ner,
) = StringUtils.find_head_lemma_pos_ner(str(mention_text))
if "mention_type" in mention_line:
mention_type = mention_line["mention_type"]
if "score" in mention_line:
score = mention_line["score"]
if "is_continuous" in mention_line:
is_continue = mention_line["is_continuous"]
if "is_singleton" in mention_line:
is_singleton = mention_line["is_singleton"]
if "predicted_coref_chain" in mention_line:
predicted_coref_chain = mention_line["predicted_coref_chain"]
if "mention_index" in mention_line:
mention_index = mention_line["mention_index"]
mention_data = MentionData(
topic_id,
doc_id,
sent_id,
tokens_numbers,
mention_text,
mention_context,
mention_head,
mention_head_lemma,
coref_chain,
mention_type,
is_continue,
is_singleton,
score,
predicted_coref_chain,
mention_pos,
mention_ner,
mention_index,
)
except Exception:
print("Unexpected error:", sys.exc_info()[0])
raise Exception("failed reading json line-" + str(mention_line))
return mention_data
