mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
fixing all languages
This commit is contained in:
parent
b509a3e7fc
commit
b221bcf1ba
|
@ -31,16 +31,15 @@ def noun_chunks(obj):
|
||||||
if word.i in seen:
|
if word.i in seen:
|
||||||
continue
|
continue
|
||||||
if word.dep in np_deps:
|
if word.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
|
||||||
continue
|
|
||||||
flag = False
|
flag = False
|
||||||
if word.pos == NOUN:
|
if word.pos == NOUN:
|
||||||
# check for patterns such as γραμμή παραγωγής
|
# check for patterns such as γραμμή παραγωγής
|
||||||
for potential_nmod in word.rights:
|
for potential_nmod in word.rights:
|
||||||
if potential_nmod.dep == nmod:
|
if potential_nmod.dep == nmod:
|
||||||
seen.update(
|
w_range = range(word.left_edge.i, potential_nmod.i + 1)
|
||||||
j for j in range(word.left_edge.i, potential_nmod.i + 1)
|
if any(j in seen for j in w_range):
|
||||||
)
|
continue
|
||||||
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, potential_nmod.i + 1, np_label
|
yield word.left_edge.i, potential_nmod.i + 1, np_label
|
||||||
flag = True
|
flag = True
|
||||||
break
|
break
|
||||||
|
@ -54,9 +53,10 @@ def noun_chunks(obj):
|
||||||
head = head.head
|
head = head.head
|
||||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||||
if head.dep in np_deps:
|
if head.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.i + 1, np_label
|
yield word.left_edge.i, word.i + 1, np_label
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -36,9 +36,10 @@ def noun_chunks(obj):
|
||||||
if word.i in seen:
|
if word.i in seen:
|
||||||
continue
|
continue
|
||||||
if word.dep in np_deps:
|
if word.dep in np_deps:
|
||||||
if any(j in seen for j in range(word.left_edge.i, word.i + 1)):
|
w_range = range(word.left_edge.i, word.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.i + 1, np_label
|
yield word.left_edge.i, word.i + 1, np_label
|
||||||
elif word.dep == conj:
|
elif word.dep == conj:
|
||||||
head = word.head
|
head = word.head
|
||||||
|
@ -46,9 +47,10 @@ def noun_chunks(obj):
|
||||||
head = head.head
|
head = head.head
|
||||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||||
if head.dep in np_deps:
|
if head.dep in np_deps:
|
||||||
if any(j in seen for j in range(word.left_edge.i, word.i + 1)):
|
w_range = range(word.left_edge.i, word.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.i + 1, np_label
|
yield word.left_edge.i, word.i + 1, np_label
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -36,9 +36,10 @@ def noun_chunks(obj):
|
||||||
if word.i in seen:
|
if word.i in seen:
|
||||||
continue
|
continue
|
||||||
if word.dep in np_deps:
|
if word.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.i + 1, np_label
|
yield word.left_edge.i, word.i + 1, np_label
|
||||||
elif word.dep == conj:
|
elif word.dep == conj:
|
||||||
head = word.head
|
head = word.head
|
||||||
|
@ -46,9 +47,10 @@ def noun_chunks(obj):
|
||||||
head = head.head
|
head = head.head
|
||||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||||
if head.dep in np_deps:
|
if head.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.i + 1, np_label
|
yield word.left_edge.i, word.i + 1, np_label
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -35,9 +35,10 @@ def noun_chunks(obj):
|
||||||
if word.i in seen:
|
if word.i in seen:
|
||||||
continue
|
continue
|
||||||
if word.dep in np_deps:
|
if word.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
elif word.dep == conj:
|
elif word.dep == conj:
|
||||||
head = word.head
|
head = word.head
|
||||||
|
@ -45,9 +46,10 @@ def noun_chunks(obj):
|
||||||
head = head.head
|
head = head.head
|
||||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||||
if head.dep in np_deps:
|
if head.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -35,9 +35,10 @@ def noun_chunks(obj):
|
||||||
if word.i in seen:
|
if word.i in seen:
|
||||||
continue
|
continue
|
||||||
if word.dep in np_deps:
|
if word.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
elif word.dep == conj:
|
elif word.dep == conj:
|
||||||
head = word.head
|
head = word.head
|
||||||
|
@ -45,9 +46,10 @@ def noun_chunks(obj):
|
||||||
head = head.head
|
head = head.head
|
||||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||||
if head.dep in np_deps:
|
if head.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -35,9 +35,10 @@ def noun_chunks(obj):
|
||||||
if word.i in seen:
|
if word.i in seen:
|
||||||
continue
|
continue
|
||||||
if word.dep in np_deps:
|
if word.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
elif word.dep == conj:
|
elif word.dep == conj:
|
||||||
head = word.head
|
head = word.head
|
||||||
|
@ -45,9 +46,10 @@ def noun_chunks(obj):
|
||||||
head = head.head
|
head = head.head
|
||||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||||
if head.dep in np_deps:
|
if head.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -36,9 +36,10 @@ def noun_chunks(obj):
|
||||||
if word.i in seen:
|
if word.i in seen:
|
||||||
continue
|
continue
|
||||||
if word.dep in np_deps:
|
if word.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
elif word.dep == conj:
|
elif word.dep == conj:
|
||||||
head = word.head
|
head = word.head
|
||||||
|
@ -46,9 +47,10 @@ def noun_chunks(obj):
|
||||||
head = head.head
|
head = head.head
|
||||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||||
if head.dep in np_deps:
|
if head.dep in np_deps:
|
||||||
if any(w.i in seen for w in word.subtree):
|
w_range = range(word.left_edge.i, word.right_edge.i + 1)
|
||||||
|
if any(j in seen for j in w_range):
|
||||||
continue
|
continue
|
||||||
seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1))
|
seen.update(j for j in w_range)
|
||||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue
Block a user