forked from kristjan/cjvt-valency
bug fix: adding _ to adjective headwords
This commit is contained in:
@@ -1,3 +1,6 @@
|
|||||||
|
# Deprecated: headword creation moved to be part of corpusparser,
|
||||||
|
# index creation moved to app.py as a preprocessing (with exit) step
|
||||||
|
|
||||||
CORPORA = ["kres", "ssj"]
|
CORPORA = ["kres", "ssj"]
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
|
|||||||
Submodule src/pkg/cjvt-corpusparser updated: af4f6045bb...c6b8426fb3
@@ -1,4 +1,5 @@
|
|||||||
import logging
|
import logging
|
||||||
|
from corpusparser import enriched_lemma
|
||||||
|
|
||||||
log = logging.getLogger(__name__)
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
@@ -20,7 +21,7 @@ def frames_from_db_entry(dbent):
|
|||||||
srldict[key] += [srl]
|
srldict[key] += [srl]
|
||||||
for hwtid, srlarr in srldict.items():
|
for hwtid, srlarr in srldict.items():
|
||||||
frames += [Frame(
|
frames += [Frame(
|
||||||
hw_lemma=token_dict[hwtid]["lemma"],
|
hw_lemma=enriched_lemma(token_dict[hwtid]),
|
||||||
tids=[_full_tid(hwtid)],
|
tids=[_full_tid(hwtid)],
|
||||||
slots=[
|
slots=[
|
||||||
Slot(
|
Slot(
|
||||||
|
|||||||
Reference in New Issue
Block a user