explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-06 06:03:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add hack to deprojectivize to handle cycles

Browse Source
This commit is contained in:
Adriane Boyd 2020-10-12 14:17:33 +02:00
parent 4fa967ea84
commit 4a38a698d5
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/pipeline/_parser_internals/nonproj.pyx
View File

@ -112,12 +112,21 @@ cpdef deprojectivize(Doc doc):
# Reattach arcs with decorated labels (following HEAD scheme). For each # Reattach arcs with decorated labels (following HEAD scheme). For each
# decorated arc X||Y, search top-down, left-to-right, breadth-first until # decorated arc X||Y, search top-down, left-to-right, breadth-first until
# hitting a Y then make this the new head. # hitting a Y then make this the new head.
orig_heads = [t.head.i for t in doc]
orig_deps = [t.dep_ for t in doc]
for i in range(doc.length): for i in range(doc.length):
label = doc.vocab.strings[doc.c[i].dep] label = doc.vocab.strings[doc.c[i].dep]
if DELIMITER in label: if DELIMITER in label:
new_label, head_label = label.split(DELIMITER) new_label, head_label = label.split(DELIMITER)
new_head = _find_new_head(doc[i], head_label) new_head = _find_new_head(doc[i], head_label)
doc.c[i].head = new_head.i - i if new_head is not None:
doc.c[i].head = new_head.i - i
else:
print(i, doc.text, [t.text for t in doc], orig_heads, orig_deps)
if i == 0:
doc.c[i].head = 0
else:
doc.c[i].head = -1
doc.c[i].dep = doc.vocab.strings.add(new_label) doc.c[i].dep = doc.vocab.strings.add(new_label)
set_children_from_heads(doc.c, 0, doc.length) set_children_from_heads(doc.c, 0, doc.length)
return doc return doc
@ -165,7 +174,11 @@ def _find_new_head(token, headlabel):
# returns the id of the first descendant with the given label # returns the id of the first descendant with the given label
# if there is none, return the current head (no change) # if there is none, return the current head (no change)
queue = [token.head] queue = [token.head]
n_iter = 0
while queue: while queue:
if n_iter > len(token.doc):
return None
n_iter += 1
next_queue = [] next_queue = []
for qtoken in queue: for qtoken in queue:
for child in qtoken.children: for child in qtoken.children: