def simp_syn_sent(sent):
strs = ""
# the original tokens in the sent
#import pdb; pdb.set_trace()
#print "syn sent: ", sent
#import pdb; pdb.set_trace()
tokens = StanfordTokenizer().tokenize(sent)
tokens.insert(0, '')
result = list(eng_parser.raw_parse(sent))[0]
root = result.root['word']
#w = result.tree()
#print "parse_tree:", w
#TODO: use the tree structure, check again
node_list = [] # dict (4 -> 4, u'said', u'VBD', u'root', [[18], [22], [16], [3]])
for node in result.nodes.items():
node_list.append(base.get_triples(node))
#node_list[base.get_triples[0]] = base.get_triples(node)
#import pdb; pdb.set_trace()
if len(sent) > 0:
strs = simp_coordi_sent(tokens, node_list)
if len(strs) > 0:
return strs
else:
strs = simp_subordi_sent(tokens, node_list)
if len(strs) > 0:
return strs
else:
strs = simp_advcl_sent(tokens, node_list)
if len(strs) > 0:
return strs
else:
strs = simp_parti_sent(tokens, node_list)
if len(strs) > 0:
return strs
else:
strs = simp_adjec_sent(tokens, node_list)
if len(strs) > 0:
return strs
else:
strs = simp_appos_sent(tokens, node_list)
if len(strs) > 0:
return strs
else:
strs = simp_passive_sent(tokens, node_list)
if len(strs) > 0:
return strs
return strs
def simp_syn_sent_(sent):
strs = ""
# the original tokens in the sent
"""
lst1 = "Peter, who liked fruits, ate an apple.".split()
_lst = sent.split()
#import pdb; pdb.set_trace()
if lst1 == _lst:
return "Peter liked fruits. Peter ate an apple."
"""
#import pdb; pdb.set_trace()
#print(sent)
#import pdb; pdb.set_trace()
tokens = StanfordTokenizer().tokenize(str(sent))
#tokens = wordpunct_tokenize(str(sent))
tokens.insert(0, '')
result = list(eng_parser.raw_parse(sent))[0]
root = result.root['word']
#import pdb; pdb.set_trace()
#w = result.tree()
#print "parse_tree:", w
#for row in result.triples():
# print(row)
#import pdb; pdb.set_trace()
#TODO: use the tree structure, check again
node_list = [] # dict (4 -> 4, u'said', u'VBD', u'root', [[18], [22], [16], [3]])
for node in result.nodes.items():
node_list.append(base.get_triples(node))
#node_list[base.get_triples[0]] = base.get_triples(node)
#import pdb; pdb.set_trace()
#strs = simp_coordi_sent(tokens, node_list)
#strs = simp_subordi_sent(tokens, node_list)
#strs = simp_advcl_sent(tokens, node_list)
#strs = simp_parti_sent(tokens, node_list)
strs = simp_adjec_sent(tokens, node_list)
#strs = simp_appos_sent(tokens, node_list)
#strs = simp_passive_sent(tokens, node_list)
return strs
def simp_syn_sent_(sent):
strs = ""
#print(sent)
#import pdb; pdb.set_trace()
tokens = StanfordTokenizer().tokenize(str(sent))
#tokens = wordpunct_tokenize(str(sent))
tokens.insert(0, '')
re = list(eng_parser.raw_parse(sent))[0]
root = re.root['word']
node_list = [] # dict (4 -> 4, u'said', u'VBD', u'root', [[18], [22], [16], [3]])
for node in re.nodes.items():
node_list.append(base.get_triples(node))
#result = list(eng_parser.raw_parse(sent))[0]
#root = result.root['word']
strs = simp_relcl_sent(tokens, node_list)
return strs
def _simp_syn_sent(sent, _algs=range(1,10)):
strs = ""
"""
# order the ALG for the better performance(precision/recall)
_algs_lst_ = [
paratax.simp_paratax_sent,
#punct.simp_punct_sent,
subordi.simp_subordi_sent,
adverb.simp_adverb_sent,
parti.simp_parti_sent,
appos.simp_appos_sent,
adjec.simp_adjec_sent,
coordi.simp_coordi_sent,
passive.simp_passive_sent
]
"""
# the original tokens in the sent
#print "syn sent: ", sent
#import pdb; pdb.set_trace()
tokens = StanfordTokenizer().tokenize(sent)
#tokens = wordpunct_tokenize(strs)
tokens.insert(0, '')
#taggers = eng_tagger.tag(sent.split())
result = list(eng_parser.raw_parse(sent))[0]
root = result.root['word']
#w = result.tree()
#print "parse_tree:", w
#TODO: use the tree structure, Check again
node_list = [] # dict (4 -> 4, u'said', u'VBD', u'root', [[18], [22], [16], [3]])
for node in result.nodes.items():
node_list.append(base.get_triples(node))
#node_list[base.get_triples[0]] = base.get_triples(node)
alg = ""
"""
#import pdb; pdb.set_trace()
if len(sent) > 0:
for ind in _algs:
#import pdb; pdb.set_trace()
# if the alg in the choices
print "_alg: ", _algs_lst[ind]
if len(strs) > 0:
return strs, _algs_lst[ind]
else:
#func = _algs_lst[ind]
strs = _algs_lst[ind](tokens,node_list)
"""
# Use the robest function for the experiments
if len(sent) > 0:
strs = paratax.simp_paratax_sent(tokens, node_list)
if len(strs) > 0:
alg = "paratax"
return strs, alg
else:
strs = punct.simp_punct_sent(tokens, node_list)
if len(strs) > 0:
alg = "punct"
return strs, alg
else:
#strs = coordi.simp_coordi_sent(tokens, node_list)
strs = subordi.simp_subordi_sent(tokens, node_list)
if len(strs) > 0:
alg = "subordi"
return strs, alg
else:
strs = adverb.simp_adverb_sent(tokens, node_list)
if len(strs) > 0:
alg = "adverb"
return strs, alg
else:
strs = parti.simp_parti_sent(tokens, node_list)
if len(strs) > 0:
alg = "parti"
return strs, alg
else:
strs = appos.simp_appos_sent(tokens, node_list)
if len(strs) > 0:
alg = "appos"
return strs, alg
else:
strs = adjec.simp_adjec_sent(tokens, node_list)
if len(strs) > 0:
alg = "adjec"
return strs, alg
else:
#strs = subordi.simp_subordi_sent(tokens, node_list)
strs = coordi.simp_coordi_sent(tokens, node_list)
if len(strs) > 0:
alg = "coordi"
return strs, alg
else:
strs = passive.simp_passive_sent(tokens, node_list)
if len(strs) > 0:
alg = "passive"
return strs, alg
else:
strs = relcl.simp_relcl_sent(tokens, node_list)
if len(strs) > 0:
alg= "relcl"
return strs, alg
return strs, alg
def relcl(sent):
strs = ""
#print(sent)
#import pdb; pdb.set_trace()
tokens = StanfordTokenizer().tokenize(str(sent))
#tokens = wordpunct_tokenize(str(sent))
tokens.insert(0, '')
re = list(eng_parser.raw_parse(sent))[0]
root = re.root['word']
node_list = [] # dict (4 -> 4, u'said', u'VBD', u'root', [[18], [22], [16], [3]])
for node in re.nodes.items():
node_list.append(base.get_triples(node))
#result = list(eng_parser.raw_parse(sent))[0]
#root = result.root['word']
#strs = simp_relcl_sent(tokens, node_list)
dep = eng_parser.raw_parse(sent).next()
result = list(dep.triples())
nsubj = ""
verb = ""
for node in result:
if 'acl:relcl' in node[1]:
#import pdb; pdb.set_trace()
nsubj = node[0][0]
verb = node[2][0]
#break
#import pdb; pdb.set_trace()
nsubj_ind = tokens.index(nsubj)
verb_ind = tokens.index(verb)
#split_ind = tokens.index(COMMA)
#import pdb; pdb.set_trace()
#if split_ind < verb_ind:
_str1 = tokens[:nsubj_ind+1]
str1 = ' '.join(_str1) + " . "
_str2 = tokens[nsubj_ind+1:]
if _str2[0] in PUNCTUATION:
_str2.pop(0)
if ('which' in _str2[0]) or ('who' in _str2[0]):
_str2.pop(0)
str2 = base.replace_nsubj(tokens, nsubj) + ' '.join(_str2)
strs = str1 + str2
"""
stree = [parse.tree() for parse in eng_parser.raw_parse(sent)][0]
#import pdb; pdb.set_trace()
for postn in stree.treepositions():
if stree.label().endswith("=H"):
parentpos = postn[:-1]
partial = Tree(stree[parentpos].label(), [ stree[postn] ])
"""
#import pdb; pdb.set_trace()
#strs = simp_relcl_sent(result)
"""
lst = []
se = 0
head = ""
dependent = ""
for nd in re:
if 'nsubj' in nd[1] or 'nsubjpass' in nd[1]:
head = nd[0][0]
dependent = nd[2][0]
"""
#for node in node_list[1:]:
return strs