explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-03 21:24:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix whitespace attachment in simpler way. Leaves problem with setting left/right children.

Browse Source
This commit is contained in:
Matthew Honnibal 2015-10-13 18:23:24 +11:00
parent 883ff1f59e
commit 37919eac82
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/syntax/arc_eager.pyx
View File

@ -384,10 +384,7 @@ cdef class ArcEager(TransitionSystem):
for i in range(st.length): for i in range(st.length):
# Always attach spaces to the previous word # Always attach spaces to the previous word
if Lexeme.c_check_flag(st._sent[i].lex, IS_SPACE): if Lexeme.c_check_flag(st._sent[i].lex, IS_SPACE):
if i >= 1: st._sent[i].head = -1 if (i >= 1) else 1
st.add_arc(i-1, i, st._sent[i].dep)
else:
st.add_arc(i+1, i, st._sent[i].dep)
if st._sent[i].sent_start and st._sent[i].head == -1: if st._sent[i].sent_start and st._sent[i].head == -1:
st._sent[i].sent_start = False st._sent[i].sent_start = False
# If we had this space token as the start of a sentence, # If we had this space token as the start of a sentence,