def get_features(ptree: nltk.ParentedTree, conn_idxs):
leave_list = ptree.leaves()
lca_loc = ptree.treeposition_spanning_leaves(conn_idxs[0], conn_idxs[-1] + 1)[:-1]
self_category = ptree[lca_loc].label()
parent_category = ptree[lca_loc].parent().label() if lca_loc else self_category
left_sibling = get_sibling_label(ptree[lca_loc], 'left')
right_sibling = get_sibling_label(ptree[lca_loc], 'right')
labels = {n.label() for n in ptree.subtrees(lambda t: t.height() > 2)}
bool_vp = 'VP' in labels
bool_trace = 'T' in labels
c = ' '.join(leave_list[conn_idxs[0]:conn_idxs[-1] + 1]).lower()
prev, prev_conn, prev_pos, prev_pos_conn_pos = get_pos_features(ptree, conn_idxs, c, -1)
next, next_conn, next_pos, next_pos_conn_pos = get_pos_features(ptree, conn_idxs, c, 1)
prev = lemmatizer.lemmatize(prev)
next = lemmatizer.lemmatize(next)
r2l = [ptree[lca_loc[:i + 1]].label() for i in range(len(lca_loc))]
r2lcomp = get_compressed_chain(r2l)
feat = {'connective': c, 'connectivePOS': self_category,
'prevWord': prev, 'prevPOSTag': prev_conn, 'prevPOS+cPOS': prev_pos_conn_pos,
'nextWord': next, 'nextPOSTag': next_pos, 'cPOS+nextPOS': next_pos_conn_pos,
'root2LeafCompressed': ','.join(r2lcomp), 'root2Leaf': ','.join(r2l),
'left_sibling': left_sibling, 'right_sibling': right_sibling,
'parentCategory': parent_category, 'boolVP': bool_vp, 'boolTrace': bool_trace}
return feat
def get_features(relation: Relation, ptree: nltk.ParentedTree):
conn_raw = ' '.join(t.surface for t in relation.conn.tokens)
conn_idxs = [t.local_idx for t in relation.conn.tokens]
lca_loc = lca(ptree, conn_idxs)
conn_tag = ptree[lca_loc].label()
if conn_idxs[0] == 0:
prev = "NONE"
else:
prev = ptree.leaves()[conn_idxs[0] - 1][0]
prev = lemmatizer.lemmatize(prev)
conn_pos_relative = get_connective_sentence_position(conn_idxs, ptree)
feat = {'Connective': conn_raw,
'ConnectivePOS': conn_tag,
'ConnectivePrev': prev, 'connectivePosition': conn_pos_relative}
return feat
tree=NewForest[index]
tree_str1=tree.pprint(margin=10000)
tree_str2=remove_all_subscript(tree).pprint(margin=10000)
tree_str3=remove_crl_subscript(tree).pprint(margin=10000)
#
# blocking substituting '_' between tag and subtag, into white spaces, !!! ### diff from refined_word_structure_gen
#
#new_tree_str1=' '.join([i[:-2]+' '+c2l(i[-1]) if len(i)>1 and i[-2]=='_' else i for i in tree_str1.split()]) # remove '_' to merge subscript to merge it to the non-terminal
#new_tree_str2=tree_str2
#new_tree_str3=' '.join([i[:-2]+' '+c2l(i[-1]) if len(i)>1 and i[-2]=='_' else i for i in tree_str3.split()]) # remove '_' to merge subscript to merge Annotation1.append((new_tree_str1, counter))
Corpus1.append(''.join(tree.leaves())+' '+tree_str1)
Corpus2.append(''.join(tree.leaves())+' '+tree_str2)
Corpus3.append(''.join(tree.leaves())+' '+tree_str3)
print('\ndone!')
p2='../working_data/word_str_annotation1.zpar'
p3='../working_data/word_str_annotation2.zpar'
p4='../working_data/word_str_annotation3.zpar'
if len(sys.argv)>4:
p2=sys.argv[2]
p3=sys.argv[3]
p4=sys.argv[4]
def getHead(syntac_sen):
t = ParentedTree(syntac_sen.text)
target = t[0]
while target.height() != 2:
### non-trivial rules: no.1
flag = 0
parent = target
if target.node == "SBARQ":
for ts in target:
if ts.node in ["WHNP", "WHPP", "WHADJP", "WHADVP"] and len(ts) > 1:
target = ts
flag = 1
break
###
if not flag:
rules = head_trace_rule[target.node]
#rules = head_trace_rule.get(target.node, [])
for rule in rules:
if rule[0] == "L":
newTarget = LookByL(target, rule[1:])
elif rule[0] == "R":
newTarget = LookByR(target, rule[1:])
elif rule[0] == "LBP":
newTarget = LookByLBP(target, rule[1:])
elif rule[0] == "RBP":
newTarget = LookByRBP(target, rule[1:])
if newTarget != "":
break
if newTarget == "":
target = target[0]
else:
target = newTarget
#print target
#print target.height()
### non-trivial rules: no.2:
if flag:
leafPos = getLeafPOS(target)
m = re.search(r'(NN|NNS)_(\d+) POS_', leafPos)
if m != None:
lvs = target.leaves()
print m.groups()
target = ParentedTree("("+m.group(1)+" "+lvs[int(m.group(2))]+")")
### non-trivial rules: no.3
if target.height() == 2 and target.leaves()[0] in ["name", "kind", "type", "genre", "group", "part"]:
print parent
for k in parent:
if k.node == "PP":
target = k
break
pr = parent.right_sibling()
for p in pr:
if pr.node == "PP":
target = pr
break
return target.leaves()[0]
def getHead(syntac_sen):
t = ParentedTree(syntac_sen.text)
target = t[0]
while target.height() != 2:
### non-trivial rules: no.1
flag = 0
parent = target
if target.node == "SBARQ":
for ts in target:
if ts.node in ["WHNP", "WHPP", "WHADJP", "WHADVP"
] and len(ts) > 1:
target = ts
flag = 1
break
###
if not flag:
rules = head_trace_rule[target.node]
#rules = head_trace_rule.get(target.node, [])
for rule in rules:
if rule[0] == "L":
newTarget = LookByL(target, rule[1:])
elif rule[0] == "R":
newTarget = LookByR(target, rule[1:])
elif rule[0] == "LBP":
newTarget = LookByLBP(target, rule[1:])
elif rule[0] == "RBP":
newTarget = LookByRBP(target, rule[1:])
if newTarget != "":
break
if newTarget == "":
target = target[0]
else:
target = newTarget
#print target
#print target.height()
### non-trivial rules: no.2:
if flag:
leafPos = getLeafPOS(target)
m = re.search(r'(NN|NNS)_(\d+) POS_', leafPos)
if m != None:
lvs = target.leaves()
print m.groups()
target = ParentedTree("(" + m.group(1) + " " +
lvs[int(m.group(2))] + ")")
### non-trivial rules: no.3
if target.height() == 2 and target.leaves()[0] in [
"name", "kind", "type", "genre", "group", "part"
]:
print parent
for k in parent:
if k.node == "PP":
target = k
break
pr = parent.right_sibling()
for p in pr:
if pr.node == "PP":
target = pr
break
return target.leaves()[0]