explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-11 09:00:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add get_aligned_parse method in Example

Browse Source 
Fix Example.get_aligned_parse
This commit is contained in:
Matthew Honnibal 2020-06-21 17:16:26 +02:00
parent 6fa9a19e52
commit 59098a5f62
1 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
spacy/gold/example.pyx
View File

@ -7,6 +7,8 @@ from .align cimport Alignment
from .iob_utils import biluo_to_iob, biluo_tags_from_offsets, biluo_tags_from_doc from .iob_utils import biluo_to_iob, biluo_tags_from_offsets, biluo_tags_from_doc
from .align import Alignment from .align import Alignment
from ..errors import Errors, AlignmentError from ..errors import Errors, AlignmentError
from ..structs cimport TokenC
from ..syntax import nonproj
cpdef Doc annotations2doc(vocab, tok_annot, doc_annot): cpdef Doc annotations2doc(vocab, tok_annot, doc_annot):
@ -121,6 +123,23 @@ cdef class Example:
output = [vocab.strings[o] if o is not None else o for o in output] output = [vocab.strings[o] if o is not None else o for o in output]
return output return output
def get_aligned_parse(self, projectivize=True):
cand_to_gold = self.alignment.cand_to_gold
gold_to_cand = self.alignment.gold_to_cand
aligned_heads = [None] * self.x.length
aligned_deps = [None] * self.x.length
heads = [token.head.i for token in self.y]
deps = [token.dep_ for token in self.y]
heads, deps = nonproj.projectivize(heads, deps)
for cand_i in range(self.x.length):
gold_i = cand_to_gold[cand_i]
if gold_i is not None: # Alignment found
gold_head = gold_to_cand[heads[gold_i]]
if gold_head is not None:
aligned_heads[cand_i] = gold_head
aligned_deps[cand_i] = deps[gold_i]
return aligned_heads, aligned_deps
def to_dict(self): def to_dict(self):
return { return {
"doc_annotation": { "doc_annotation": {