explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Constrain subtok to adjacent words

Browse Source
This commit is contained in:
Matthew Honnibal 2018-04-08 14:50:21 +02:00
parent b43bfd3524
commit 8f21953fc5
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/syntax/arc_eager.pyx
View File

@ -180,6 +180,8 @@ cdef class Reduce:
cdef class LeftArc: cdef class LeftArc:
@staticmethod @staticmethod
cdef bint is_valid(const StateC* st, attr_t label) nogil: cdef bint is_valid(const StateC* st, attr_t label) nogil:
if label == SUBTOK_LABEL and st.S(0).i != (st.B(0).i-1):
return 0
sent_start = st._sent[st.B_(0).l_edge].sent_start sent_start = st._sent[st.B_(0).l_edge].sent_start
return sent_start != 1 return sent_start != 1
@ -216,6 +218,8 @@ cdef class RightArc:
@staticmethod @staticmethod
cdef bint is_valid(const StateC* st, attr_t label) nogil: cdef bint is_valid(const StateC* st, attr_t label) nogil:
# If there's (perhaps partial) parse pre-set, don't allow cycle. # If there's (perhaps partial) parse pre-set, don't allow cycle.
if label == SUBTOK_LABEL and st.S(0).i != (st.B(0).i-1):
return 0
sent_start = st._sent[st.B_(0).l_edge].sent_start sent_start = st._sent[st.B_(0).l_edge].sent_start
return sent_start != 1 and st.H(st.S(0)) != st.B(0) return sent_start != 1 and st.H(st.S(0)) != st.B(0)