mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 09:26:27 +03:00
Merge pull request #5019 from questoph/master
Optimizing tokenization for Luxembourgish (dealing with apostrophe infixes)
This commit is contained in:
commit
d50152b917
|
@ -5,11 +5,13 @@ from ..char_classes import LIST_ELLIPSES, LIST_ICONS, ALPHA, ALPHA_LOWER, ALPHA_
|
|||
|
||||
ELISION = " ' ’ ".strip().replace(" ", "")
|
||||
|
||||
abbrev = ("d", "D")
|
||||
|
||||
_infixes = (
|
||||
LIST_ELLIPSES
|
||||
+ LIST_ICONS
|
||||
+ [
|
||||
r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION),
|
||||
r"(?<=^[{ab}][{el}])(?=[{a}])".format(ab=abbrev, a=ALPHA, el=ELISION),
|
||||
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
|
||||
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
|
||||
r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),
|
||||
|
|
|
@ -10,6 +10,8 @@ _exc = {}
|
|||
|
||||
# translate / delete what is not necessary
|
||||
for exc_data in [
|
||||
{ORTH: "’t", LEMMA: "et", NORM: "et"},
|
||||
{ORTH: "’T", LEMMA: "et", NORM: "et"},
|
||||
{ORTH: "'t", LEMMA: "et", NORM: "et"},
|
||||
{ORTH: "'T", LEMMA: "et", NORM: "et"},
|
||||
{ORTH: "wgl.", LEMMA: "wannechgelift", NORM: "wannechgelift"},
|
||||
|
|
Loading…
Reference in New Issue
Block a user