KoichiYasuoka's picture
model improved
42776d8
raw
history blame contribute delete
607 Bytes
#! /usr/bin/python3
src="DeepPavlov/rubert-base-cased"
tgt="KoichiYasuoka/bert-base-russian-upos"
import os,sys
url="https://github.com/UniversalDependencies/UD_Russian-"
for e in ["Taiga","SynTagRus","GSD","Poetry"]:
u=url+e
d=os.path.basename(u)
os.system("test -d "+d+" || git clone --depth=1 "+u)
os.system("for F in train dev test ; do cat UD_Russian-*/*-$F*.conllu > $F.conllu ; done ; cat *.conllu > train.upos")
os.system(f"{sys.executable} -m esupar.train {src} {tgt} -16 /tmp train.upos")
os.system(f"{sys.executable} -m esupar.train {tgt} {tgt} 16 /// train.conllu dev.conllu test.conllu")