Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Add a linear scan to Span.root method, to help with long sentences

This commit is contained in:
Matthew Honnibal 2016-01-16 16:17:28 +01:00
parent ca0a603fde
commit 304339985e
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/tokens/span.pyx
View File

@ -170,6 +170,19 @@ cdef class Span:
# This should probably be called 'head', and the other one called # This should probably be called 'head', and the other one called
# 'gov'. But we went with 'head' elsehwhere, and now we're stuck =/ # 'gov'. But we went with 'head' elsehwhere, and now we're stuck =/
cdef int i cdef int i
# First, we scan through the Span, and check whether there's a word
# with head==0, i.e. a sentence root. If so, we can return it. The
# longer the span, the more likely it contains a sentence root, and
# in this case we return in linear time.
for i in range(self.start, self.end):
if self.doc.c[i].head == 0:
return i
# If we don't have a sentence root, we do something that's not so
# algorithmically clever, but I think should be quite fast, especially
# for short spans.
# For each word, we count the path length, and arg min this measure.
# We could use better tree logic to save steps here...But I think this
# should be okay.
cdef int current_best = _count_words_to_root(&self.doc.c[self.start], cdef int current_best = _count_words_to_root(&self.doc.c[self.start],
self.doc.length) self.doc.length)
cdef int root = self.start cdef int root = self.start