def create(rows):
instance = NLPInstance()
instance.addToken().addProperty(name="Word", value="-Root-")
predicates = []
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[1]).\
addProperty(name="Index", value=row[0]).\
addProperty(name="Lemma", value=row[2]).\
addProperty(name="PLemma", value=row[3]).\
addProperty(name="PoS", value=row[4]).\
addProperty(name="PPoS", value=row[5]).\
addProperty(name="Feat", value=row[6]).\
addProperty(name="PFeat", value=row[7])
if row[13] != "_":
index = int(row[0])
predicates.append(index)
instance.addSpan(str(index), str(index), row[13], "sense")
for row in rows:
row = row.strip().split()
# dependency
if row[8] != "_":
instance.addDependency(From=str(row[8]), to=str(row[0]), label=row[10], type="dep")
if row[9] != "_":
instance.addDependency(From=str(row[9]), to=str(row[0]), label=row[11], type="pdep")
# role
for col in range(14, len(row)):
label = row[col]
if label != "_":
pred = predicates[col-14]
arg = int(row[0])
# if arg != pred:
instance.addDependency(From=str(pred), to=str(arg), label=label, type="role")
return instance
def create(rows):
instance = NLPInstance()
instance.addToken().addProperty("Word", "-Root-")
predicates = []
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[1]).\
addProperty(name="Index", value=str(row[0])).\
addProperty(name="Lemma", value=row[2]).\
addProperty(name="Pos", value=row[3]).\
addProperty(name="Split Form", value=row[5]).\
addProperty(name="Split Lemma", value=row(6)).\
addProperty(name="Split PoS", value=row[7])
if row[10] != "_":
index = int(row[0])
predicates.append(index)
instance.addSpan(str(index), str(index), row[10], "sense")
for row in rows:
row = row.strip().split()
# dependency
if row[8] != "_":
instance.addDependency(str(row[8]), str(row[0]), row[9], "dep")
# role
for col in range(11, len(row)):
label = row[col]
if label != "_":
pred = predicates[col - 11]
arg = int(row[0])
# if arg != pred
instance.addEdge(From=pred,
to=arg,
label=label,
type="role")
return instance
def create(rows):
instance = NLPInstance()
instance.addToken().addProperty("Word", "-Root-")
predicates = []
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[1]).\
addProperty(name="Index", value=str(row[0])).\
addProperty(name="Lemma", value=row[2]).\
addProperty(name="Pos", value=row[3]).\
addProperty(name="Split Form", value=row[5]).\
addProperty(name="Split Lemma", value=row(6)).\
addProperty(name="Split PoS", value=row[7])
if row[10] != "_":
index = int(row[0])
predicates.append(index)
instance.addSpan(str(index), str(index), row[10], "sense")
for row in rows:
row = row.strip().split()
# dependency
if row[8] != "_":
instance.addDependency(str(row[8]), str(row[0]), row[9], "dep")
# role
for col in range(11, len(row)):
label = row[col]
if label != "_":
pred = predicates[col-11]
arg = int(row[0])
# if arg != pred
instance.addEdge(From=pred, to=arg, label=label, type="role")
return instance
def create(self, rows):
instance = NLPInstance()
index = 0
for row in rows:
if row == "\n":
continue
row = row.split()
chunk = row[2]
instance.addToken().\
addProperty(property = "Word", value = row[0]).\
addProperty(property = "Index", value = str(index))
instance.addSpan(index, index, row[1], "pos")
instance.addSpan(index, index, chunk, "Chunk (BIO)")
index += 1
return instance
def create(self, rows):
instance = NLPInstance()
index = 0
for row in rows:
if row == "\n":
continue
row = row.split()
instance.addToken().\
addProperty(property = "Word", value = row[0]).\
addProperty(property = "Index", value = str(index))
instance.addSpan(index, index, row[1], "ner (BIO)")
index += 1
# TODO: TabFormat.extractSpan00(rows, 1, "ner", instance)
return instance
def create(rows):
instance = NLPInstance()
index = 0
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[0]).\
addProperty(name="Index", value=str(index))
instance.addSpan(index, index, row[1], "ner (BIO)")
index += 1
tabformat = TabFormat(object) # TODO: object = MainWindow?
tabformat.extractSpan00(rows=rows, column=1, type="ner", instance=instance)
return instance
def create(rows):
instance = NLPInstance()
instance.addToken().addProperty(name="Word", value="-Root-")
predicates = []
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[1]).\
addProperty(name="Index", value=row[0]).\
addProperty(name="Lemma", value=row[2]).\
addProperty(name="PLemma", value=row[3]).\
addProperty(name="PoS", value=row[4]).\
addProperty(name="PPoS", value=row[5]).\
addProperty(name="Feat", value=row[6]).\
addProperty(name="PFeat", value=row[7])
if row[13] != "_":
index = int(row[0])
predicates.append(index)
instance.addSpan(str(index), str(index), row[13], "sense")
for row in rows:
row = row.strip().split()
# dependency
if row[8] != "_":
instance.addDependency(From=str(row[8]),
to=str(row[0]),
label=row[10],
type="dep")
if row[9] != "_":
instance.addDependency(From=str(row[9]),
to=str(row[0]),
label=row[11],
type="pdep")
# role
for col in range(14, len(row)):
label = row[col]
if label != "_":
pred = predicates[col - 14]
arg = int(row[0])
# if arg != pred:
instance.addDependency(From=str(pred),
to=str(arg),
label=label,
type="role")
return instance
def create(rows):
instance = NLPInstance()
index = 0
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[0]).\
addProperty(name="Index", value=str(index))
instance.addSpan(index, index, row[1], "ner (BIO)")
index += 1
tabformat = TabFormat(object) # TODO: object = MainWindow?
tabformat.extractSpan00(rows=rows,
column=1,
type="ner",
instance=instance)
return instance
def create(self, rows):
instance = NLPInstance()
instance.addToken().addProperty(property="Word", value="-Root-")
predicates = []
for row in rows:
if row == "\n":
continue
row = row.split()
instance.addToken().\
addProperty(property="Word", value=row[1]).\
addProperty(property="Index", value=row[0]).\
addProperty(property="Lemma", value=row[2]).\
addProperty(property="PLemma", value=row[3]).\
addProperty(property="PoS", value=row[4]).\
addProperty(property="PPoS", value=row[5]).\
addProperty(property="Feat", value=row[6]).\
addProperty(property="PFeat", value=row[7])
if row[13] != "_":
index = row[0]
predicates.append(index)
instance.addSpan(index, index, row[13], "sense")
for row in rows:
if row == "\n":
continue
row = row.split()
#dependency
if row[0] != "_":
instance.addEdge(From = row[8], to = row[0], label = row[10], type = "dep")
if row[9] != "_":
instance.addEdge(From = row[9], to = row[0], label = row[11], type = "pdep")
#role
for col in range(14, len(row)):
label = row[col]
if label != "_":
pred = predicates[col - 14]
arg = row[0]
# if arg != pred:
instance.addEdge(From = pred, to = arg, label = label, type = "role")
return instance
def create(rows):
instance = NLPInstance()
index = 0
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[0]).\
addProperty(name="Index", value=str(index))
index += 1
predicateCount = 0
index = 0
for row in rows:
row = row.strip().split()
if row[9] != "-": # TODO: nincs 9 szó ebben?
sense = row[10] + "." + row[9]
instance.addSpan(index, index, sense, "sense")
tabformat = TabFormat(object) # TODO: object = MainWindow?
tabformat.extractSpan05(rows, 11+predicateCount, "role", sense+":", instance)
predicateCount += 1
index += 1
return instance
def create(rows):
instance = NLPInstance()
index = 0
for row in rows:
row = row.strip().split()
instance.addToken().\
addProperty(name="Word", value=row[0]).\
addProperty(name="Index", value=str(index))
index += 1
predicateCount = 0
index = 0
for row in rows:
row = row.strip().split()
if row[9] != "-": # TODO: nincs 9 szó ebben?
sense = row[10] + "." + row[9]
instance.addSpan(index, index, sense, "sense")
tabformat = TabFormat(object) # TODO: object = MainWindow?
tabformat.extractSpan05(rows, 11 + predicateCount, "role",
sense + ":", instance)
predicateCount += 1
index += 1
return instance
def create(self, rows):
instance = NLPInstance()
index = 0
for row in rows:
if row == "\n":
continue
row = row.split()
instance.addToken().\
addProperty(property = "Word", value = row[0]).\
addProperty(property = "Index", value = str(index))
index += 1
predicateCount = 0
index = 0
for row in rows:
if row == "\n":
continue
row = row.split()
if row[9] != "-": # TODO: nincs 9 szó ebben?
sense = row[10] + "." + row[9]
instance.addSpan(index, index, sense, "sense")
# TODO: TabFormat.extractSpan05(ros, 11 + predicateCount, "role", sense + ":", instance
predicateCount += 1
index += 1
return instance