p209327/nlnieuws
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

cats en tags

Browse Source
This commit is contained in:
Peter Kleiweg
2026-04-01 19:30:10 +02:00
parent 1fb1867550
commit e550b58889
14 changed files with 61 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
NOS/txt2corpus.sh
View File

@@ -58,6 +58,10 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus.
cd xml
alto -o $corpus.data.dz *.xml 2> /dev/null
# telling per bericht, niet per zin
/net/corpora/nlnieuws/namen.sh -x 9 -s $corpus.data.dz > $corpus.cat.txt
/net/corpora/nlnieuws/namen.sh -x 10 -s $corpus.data.dz > $corpus.tag.txt
cd ../..
rm -fr out