explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'feature/lemmatizer' of https://github.com/explosion/spaCy into feature/lemmatizer

Browse Source
This commit is contained in:
Matthew Honnibal 2019-03-09 00:41:53 +00:00
commit b6d60d0041
2 changed files with 2 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
spacy/cli/ud/ud_train.py
View File

@ -350,7 +350,6 @@ def initialize_pipeline(nlp, docs, golds, config, device):
nlp.add_pipe(nlp.create_pipe("tagger", config={"set_morphology": False})) nlp.add_pipe(nlp.create_pipe("tagger", config={"set_morphology": False}))
nlp.add_pipe(nlp.create_pipe("morphologizer")) nlp.add_pipe(nlp.create_pipe("morphologizer"))
nlp.add_pipe(nlp.create_pipe("parser")) nlp.add_pipe(nlp.create_pipe("parser"))
assert not nlp.get_pipe("tagger").set_morphology
if config.multitask_tag: if config.multitask_tag:
nlp.parser.add_multitask_objective("tag") nlp.parser.add_multitask_objective("tag")
if config.multitask_sent: if config.multitask_sent:

11
spacy/pipeline/pipes.pyx
View File

@ -357,14 +357,6 @@ class Tagger(Pipe):
self.cfg = OrderedDict(sorted(cfg.items())) self.cfg = OrderedDict(sorted(cfg.items()))
self.cfg.setdefault("cnn_maxout_pieces", 2) self.cfg.setdefault("cnn_maxout_pieces", 2)
@property
def set_morphology(self):
return self.cfg.get("set_morphology", True)
@set_morphology.setter
def set_morphology(self, value):
self.cfg["set_morphology"] = value
@property @property
def labels(self): def labels(self):
return tuple(self.vocab.morphology.tag_names) return tuple(self.vocab.morphology.tag_names)
@ -412,6 +404,7 @@ class Tagger(Pipe):
cdef Doc doc cdef Doc doc
cdef int idx = 0 cdef int idx = 0
cdef Vocab vocab = self.vocab cdef Vocab vocab = self.vocab
assign_morphology = self.cfg.get("set_morphology", True)
for i, doc in enumerate(docs): for i, doc in enumerate(docs):
doc_tag_ids = batch_tag_ids[i] doc_tag_ids = batch_tag_ids[i]
if hasattr(doc_tag_ids, "get"): if hasattr(doc_tag_ids, "get"):
@ -419,7 +412,7 @@ class Tagger(Pipe):
for j, tag_id in enumerate(doc_tag_ids): for j, tag_id in enumerate(doc_tag_ids):
# Don't clobber preset POS tags # Don't clobber preset POS tags
if doc.c[j].tag == 0: if doc.c[j].tag == 0:
if doc.c[j].pos == 0 and self.set_morphology: if doc.c[j].pos == 0 and assign_morphology:
# Don't clobber preset lemmas # Don't clobber preset lemmas
lemma = doc.c[j].lemma lemma = doc.c[j].lemma
vocab.morphology.assign_tag_id(&doc.c[j], tag_id) vocab.morphology.assign_tag_id(&doc.c[j], tag_id)