mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 00:46:28 +03:00
span / noun chunk has +1 because end is exclusive
This commit is contained in:
parent
84d5b7ad0a
commit
51715b9f72
|
@ -36,12 +36,12 @@ def noun_chunks(doclike):
|
|||
# check for patterns such as γραμμή παραγωγής
|
||||
for potential_nmod in word.rights:
|
||||
if potential_nmod.dep == nmod:
|
||||
prev_end = potential_nmod.i + 1
|
||||
prev_end = potential_nmod.i
|
||||
yield word.left_edge.i, potential_nmod.i + 1, np_label
|
||||
flag = True
|
||||
break
|
||||
if flag is False:
|
||||
prev_end = word.i + 1
|
||||
prev_end = word.i
|
||||
yield word.left_edge.i, word.i + 1, np_label
|
||||
elif word.dep == conj:
|
||||
# covers the case: έχει όμορφα και έξυπνα παιδιά
|
||||
|
@ -50,7 +50,7 @@ def noun_chunks(doclike):
|
|||
head = head.head
|
||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||
if head.dep in np_deps:
|
||||
prev_end = word.i + 1
|
||||
prev_end = word.i
|
||||
yield word.left_edge.i, word.i + 1, np_label
|
||||
|
||||
|
||||
|
|
|
@ -36,7 +36,7 @@ def noun_chunks(doclike):
|
|||
if word.left_edge.i <= prev_end:
|
||||
continue
|
||||
if word.dep in np_deps:
|
||||
prev_end = word.i + 1
|
||||
prev_end = word.i
|
||||
yield word.left_edge.i, word.i + 1, np_label
|
||||
elif word.dep == conj:
|
||||
head = word.head
|
||||
|
@ -44,7 +44,7 @@ def noun_chunks(doclike):
|
|||
head = head.head
|
||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||
if head.dep in np_deps:
|
||||
prev_end = word.i + 1
|
||||
prev_end = word.i
|
||||
yield word.left_edge.i, word.i + 1, np_label
|
||||
|
||||
|
||||
|
|
|
@ -36,7 +36,7 @@ def noun_chunks(doclike):
|
|||
if word.left_edge.i <= prev_end:
|
||||
continue
|
||||
if word.dep in np_deps:
|
||||
prev_end = word.i + 1
|
||||
prev_end = word.i
|
||||
yield word.left_edge.i, word.i + 1, np_label
|
||||
elif word.dep == conj:
|
||||
head = word.head
|
||||
|
@ -44,7 +44,7 @@ def noun_chunks(doclike):
|
|||
head = head.head
|
||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||
if head.dep in np_deps:
|
||||
prev_end = word.i + 1
|
||||
prev_end = word.i
|
||||
yield word.left_edge.i, word.i + 1, np_label
|
||||
|
||||
|
||||
|
|
|
@ -35,7 +35,7 @@ def noun_chunks(doclike):
|
|||
if word.left_edge.i <= prev_end:
|
||||
continue
|
||||
if word.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
elif word.dep == conj:
|
||||
head = word.head
|
||||
|
@ -43,7 +43,7 @@ def noun_chunks(doclike):
|
|||
head = head.head
|
||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||
if head.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
|
||||
|
||||
|
|
|
@ -35,7 +35,7 @@ def noun_chunks(doclike):
|
|||
if word.left_edge.i <= prev_end:
|
||||
continue
|
||||
if word.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
elif word.dep == conj:
|
||||
head = word.head
|
||||
|
@ -43,7 +43,7 @@ def noun_chunks(doclike):
|
|||
head = head.head
|
||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||
if head.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
|
||||
|
||||
|
|
|
@ -35,7 +35,7 @@ def noun_chunks(doclike):
|
|||
if word.left_edge.i <= prev_end:
|
||||
continue
|
||||
if word.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
elif word.dep == conj:
|
||||
head = word.head
|
||||
|
@ -43,7 +43,7 @@ def noun_chunks(doclike):
|
|||
head = head.head
|
||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||
if head.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
|
||||
|
||||
|
|
|
@ -36,7 +36,7 @@ def noun_chunks(doclike):
|
|||
if word.left_edge.i <= prev_end:
|
||||
continue
|
||||
if word.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
elif word.dep == conj:
|
||||
head = word.head
|
||||
|
@ -44,7 +44,7 @@ def noun_chunks(doclike):
|
|||
head = head.head
|
||||
# If the head is an NP, and we're coordinated to it, we're an NP
|
||||
if head.dep in np_deps:
|
||||
prev_end = word.right_edge.i + 1
|
||||
prev_end = word.right_edge.i
|
||||
yield word.left_edge.i, word.right_edge.i + 1, np_label
|
||||
|
||||
|
||||
|
|
Loading…
Reference in New Issue
Block a user