def sr_parse(self, texts):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
"""
# Initialize parser
srparser = SRParser([],[])
srparser.init(texts)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue)
features = fg.features()
labels = self.predict(features)
# Enumerate through all possible actions ranked based on predcition scores
for i,label in enumerate(labels):
action = label2action(label)
try:
srparser.operate(action)
break # if legal action, end the loop
except ActionError:
if i < len(labels): # if not a legal action, try the next possible action
continue
else:
print "Parsing action error with {}".format(action)
sys.exit()
tree = srparser.getparsetree()
rst = RSTTree(tree=tree)
return rst
def sr_parse(self, texts, d_pos, d_dep):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
"""
# Initialize parser
srparser = SRParser([],[])
srparser.init(texts, d_pos, d_dep)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue)
features = fg.features()
label = self.predict(features)
action = label2action(label)
# The best choice here is to choose the first
# legal action
try:
srparser.operate(action)
except ActionError:
print "Parsing action error with {}".format(action)
sys.exit()
tree = srparser.getparsetree()
rst = RSTTree(tree=tree)
return rst
def sr_parse(self, texts):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
"""
# Initialize parser
srparser = SRParser([],[])
srparser.init(texts)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue)
features = fg.features()
labels = self.predict(features)
# Enumerate through all possible actions ranked based on predcition scores
for i,label in enumerate(labels):
action = label2action(label)
try:
srparser.operate(action)
break # if legal action, end the loop
except ActionError:
if i < len(labels): # if not a legal action, try the next possible action
continue
else:
print "Parsing action error with {}".format(action)
sys.exit()
tree = srparser.getparsetree()
rst = RSTTree(tree=tree)
return rst
def sr_parse(self, doc, bcvocab=None):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
:type bcvocab: dict
:param bcvocab: brown clusters
"""
# raise NotImplementedError("Not finished yet")
# Initialize parser
srparser = SRParser([], [])
srparser.init(doc)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue, doc, bcvocab)
feat = fg.features()
# label = self.predict(feat)
labels = self.rank_labels(feat)
for label in labels:
action = label2action(label)
try:
srparser.operate(action)
break
except ActionError:
# print "Parsing action error with {}".format(action)
pass
tree = srparser.getparsetree()
rst = RSTTree()
rst.asign_tree(tree)
return rst
def sr_parse(self, doc, bcvocab=None):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
:type bcvocab: dict
:param bcvocab: brown clusters
"""
# raise NotImplementedError("Not finished yet")
# Initialize parser
srparser = SRParser([], [])
srparser.init(doc)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue, doc, bcvocab)
feat = fg.features()
# label = self.predict(feat)
labels = self.rank_labels(feat)
for label in labels:
action = label2action(label)
try:
srparser.operate(action)
break
except ActionError:
# print "Parsing action error with {}".format(action)
pass
tree = srparser.getparsetree()
rst = RSTTree()
rst.asign_tree(tree)
return rst
def sr_parse(self, texts):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
"""
# Initialize parser
srparser = SRParser([], [])
srparser.init(texts)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue)
features = fg.features()
label = self.predict(features)
action = label2action(label)
# The best choice here is to choose the first
# legal action
try:
srparser.operate(action)
except ActionError:
print "Parsing action error with {}".format(action)
sys.exit()
tree = srparser.getparsetree()
rst = RSTTree(tree=tree)
return rst
def generate_samples(self):
""" Generate samples from an binary RST tree
"""
# Sample list
samplelist = []
# Parsing action
actionlist = decodeSRaction(self.tree)
# Initialize queue and stack
queue = getedunode(self.tree)
stack = []
# Start simulating the shift-reduce parsing
for action in actionlist:
# Generate features
fg = FeatureGenerator(stack, queue)
features = fg.features()
samplelist.append(features)
# Change status of stack/queue
sr = SRParser(stack, queue)
sr.operate(action)
# stack, queue = sr.getstatus()
return (actionlist, samplelist)
def generate_samples(self):
""" Generate samples from an binary RST tree
"""
# Sample list
samplelist = []
# Parsing action
actionlist = decodeSRaction(self.tree)
# Initialize queue and stack
queue = getedunode(self.tree)
stack = []
# Start simulating the shift-reduce parsing
for action in actionlist:
# Generate features
fg = FeatureGenerator(stack, queue)
features = fg.features()
samplelist.append(features)
# Change status of stack/queue
sr = SRParser(stack, queue)
sr.operate(action)
# stack, queue = sr.getstatus()
return (actionlist, samplelist)
def sr_parse(self, texts,fname):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
"""
# Initialize parser
srparser = SRParser([],[])
dep = defaultdict()
pos = defaultdict()
lines =defaultdict()
# print fname.split(".dis")[0]+'.dep'
dir = fname.split
s =fname.split(".edus")
# print fname
# st= fname
if fname.endswith(".out.edus"):
# print "yes"
s= fname.split(".out.edus")
f= open(s[0]+'.dep',"r")
data = f.read().splitlines()
for line in data:
# print line
l = line.split('@#%^&*')
dep[l[0]] = l[1]
f= open(s[0]+'.pos',"r")
data = f.read().splitlines()
for line in data:
# print line
l = line.split('@#%^&*')
pos[l[0]] = l[1].strip()
f= open(s[0]+'.line',"r")
data = f.read().splitlines()
for line in data:
# print line
l = line.split('@#%^&*')
lines[l[0]] = l[1]
srparser.init(texts,pos,dep,lines)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue)
features = fg.features()
labels = self.predict(features)
# Enumerate through all possible actions ranked based on predcition scores
for i,label in enumerate(labels):
action = label2action(label)
try:
srparser.operate(action)
break # if legal action, end the loop
except ActionError:
if i < len(labels): # if not a legal action, try the next possible action
continue
else:
print "Parsing action error with {}".format(action)
sys.exit()
tree = srparser.getparsetree()
rst = RSTTree(tree=tree)
return rst
def sr_parse(self, texts,fname):
""" Shift-reduce RST parsing based on model prediction
:type texts: list of string
:param texts: list of EDUs for parsing
"""
# Initialize parser
srparser = SRParser([],[])
dep = defaultdict()
pos = defaultdict()
lines =defaultdict()
# print fname.split(".dis")[0]+'.dep'
dir = fname.split
s =fname.split(".edus")
# print fname
# st= fname
if fname.endswith(".out.edus"):
# print "yes"
s= fname.split(".out.edus")
f= open(s[0]+'.dep',"r")
data = f.read().splitlines()
for line in data:
# print line
l = line.split('@#%^&*')
dep[l[0]] = l[1]
f= open(s[0]+'.pos',"r")
data = f.read().splitlines()
for line in data:
# print line
l = line.split('@#%^&*')
pos[l[0]] = l[1].strip()
f= open(s[0]+'.line',"r")
data = f.read().splitlines()
for line in data:
# print line
l = line.split('@#%^&*')
lines[l[0]] = l[1]
srparser.init(texts,pos,dep,lines)
# Parsing
while not srparser.endparsing():
# Generate features
stack, queue = srparser.getstatus()
# Make sure call the generator with
# same arguments as in data generation part
fg = FeatureGenerator(stack, queue)
features = fg.features()
labels = self.predict(features)
# Enumerate through all possible actions ranked based on predcition scores
for i,label in enumerate(labels):
action = label2action(label)
try:
srparser.operate(action)
break # if legal action, end the loop
except ActionError:
if i < len(labels): # if not a legal action, try the next possible action
continue
else:
print "Parsing action error with {}".format(action)
sys.exit()
tree = srparser.getparsetree()
rst = RSTTree(tree=tree)
return rst