class GerbilNIFCollection:
def __init__(self, context: str, mention: str):
self.collection = NIFCollection()
self.context = context
self.mention = mention
self.phrases = self.collection.add_context(self.context, self.mention)
@property
def turtle(self) -> str:
return self.collection.dumps(format='turtle')
def annotation2nif(collection_name, tweet):
collection = NIFCollection(uri=collection_name)
context_name = collection_name + str(tweet.idTweet)
context = collection.add_context(uri=context_name, mention=tweet.text)
if len(tweet.mentions) > 0:
for i, mention in enumerate(tweet.mentions):
if tweet.entities[i] != 'NIL':
entity = tweet.entities[i].replace(
'dbr:', 'http://dbpedia.org/resource/')
else:
entity = 'http://optic.ufsc.br/resource/NIL/'
context.add_phrase(beginIndex=int(mention[2]),
endIndex=int(mention[3]),
annotator='http://optic.ufsc.br',
taIdentRef=entity)
nif = collection.dumps(format='turtle')
return nif
from pynif import NIFCollection
import sys,os,json,re
d = json.loads(open('input/webqsp.test.entities.with_classes.json').read())
collection = NIFCollection(uri="http://sda.tech/webquestions")
for item in d:
if not item['utterance']:
continue
uid = item['question_id']
context = collection.add_context(uri="http://sda.tech/webquestions/%s"%uid,
mention=item['utterance'])
beg = 0
for entity in item['entities']:
if entity is None:
continue
context.add_phrase(taIdentRef='http://www.wikidata.org/entity/'+entity, beginIndex=beg, endIndex=beg+1)
beg+=1
generated_nif = collection.dumps(format='turtle')
f = open('webqsp.test.nif','w')
f.write(generated_nif)
f.close()
from pynif import NIFCollection
import sys, os, json, re
d = json.loads(open('test.json').read())
collection = NIFCollection(uri="http://sda.tech/lcquadv2")
for item in d:
if not item['question']:
continue
uid = item['uid']
context = collection.add_context(uri="http://sda.tech/lcquadv2/%s" % uid,
mention=item['question'])
entities = re.findall(r'wd:([Q][0-9]*)', item['sparql_wikidata'])
beg = 0
for entity in entities:
context.add_phrase(taIdentRef='http://www.wikidata.org/entity/' +
entity,
beginIndex=beg,
endIndex=beg + 1)
beg += 1
generated_nif = collection.dumps(format='turtle')
f = open('lcquad2.0.test.nif', 'w')
f.write(generated_nif)
f.close()
from pynif import NIFCollection
import sys, os, json, re
d = json.loads(open('train.json').read())
collection = NIFCollection(uri="http://lc-quad2.sda.tech")
for item in d:
if not item['question']:
continue
uid = item['uid']
context = collection.add_context(uri="http://lc-quad2.0.sda.tech/%s" % uid,
mention=item['question'])
entities = re.findall(r'wd:([Q][0-9]*)', item['sparql_wikidata'])
for entity in entities:
context.add_phrase(taIdentRef='http://www.wikidata.org/entity/' +
entity,
beginIndex=0,
endIndex=1)
generated_nif = collection.dumps(format='turtle')
f = open('lcquad2.0.train.nif', 'w')
f.write(generated_nif)
f.close()
f = open('input/graph.test.entities.json')
d = json.loads(f.read())
for item in d:
unit = {}
unit['uid'] = int(item['question_id'])
unit['question'] = item['utterance']
unit['entities'] = item['entities']
gold.append(unit)
collection = NIFCollection(uri="http://sda.tech/graphquestions")
for item in gold:
uid = item['uid']
context = collection.add_context(uri="http://sda.tech/graphquestions/%s" %
uid,
mention=item['question'])
beg = 0
for entity in item['entities']:
if entity is None:
continue
context.add_phrase(taIdentRef='http://www.wikidata.org/entity/' +
entity,
beginIndex=beg,
endIndex=beg + 1)
beg += 1
generated_nif = collection.dumps(format='turtle')
f = open('graphquestions.test.nif', 'w')
f.write(generated_nif)
f.close()
from pynif import NIFCollection
import sys,os,json,re
gold = []
f = open('annotated_wd_data_train.txt')
for line in f.readlines():
line = line.strip()
s,p,o,q = line.split('\t')
gold.append((s,q))
collection = NIFCollection(uri="http://sda.tech/simplequestions")
for idx,item in enumerate(gold):
question = item[1]
entity = item[0]
uid = idx
context = collection.add_context(uri="http://sda.tech/simplequestions/%s"%uid, mention=question)
context.add_phrase(taIdentRef='http://www.wikidata.org/entity/'+entity, beginIndex=0, endIndex=1)
generated_nif = collection.dumps(format='turtle')
f = open('simplequestions.train.nif','w')
f.write(generated_nif)
f.close()