explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

refer to _parser_internals.nonproj.DELIMITER

Browse Source
This commit is contained in:
svlandeg 2021-01-07 18:58:13 +01:00
parent 411c842a71
commit 1abeca90a6
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/cli/debug_data.py
View File

@ -12,6 +12,7 @@ from ..training import Example
from ..training.initialize import get_sourced_components
from ..schemas import ConfigSchemaTraining
from ..pipeline._parser_internals import nonproj
from ..pipeline._parser_internals.nonproj import DELIMITER
from ..language import Language
from ..util import registry, resolve_dot_names
from .. import util
@ -383,7 +384,7 @@ def debug_data(
# rare labels in projectivized train
rare_projectivized_labels = []
for label in gold_train_data["deps"]:
if gold_train_data["deps"][label] <= DEP_LABEL_THRESHOLD and "||" in label:
if gold_train_data["deps"][label] <= DEP_LABEL_THRESHOLD and DELIMITER in label:
rare_projectivized_labels.append(
f"{label}: {gold_train_data['deps'][label]}"
)

5
spacy/pipeline/dep_parser.pyx
View File

@ -9,6 +9,7 @@ from ._parser_internals.arc_eager cimport ArcEager
from .functions import merge_subtokens
from ..language import Language
from ._parser_internals import nonproj
from ._parser_internals.nonproj import DELIMITER
from ..scorer import Scorer
from ..training import validate_examples
@ -230,8 +231,8 @@ cdef class DependencyParser(Parser):
for move in self.move_names:
if "-" in move:
label = move.split("-")[1]
if "||" in label:
label = label.split("||")[1]
if DELIMITER in label:
label = label.split(DELIMITER)[1]
labels.add(label)
return tuple(sorted(labels))