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

9,10 -> C,T

Browse Source
This commit is contained in:
Peter Kleiweg
2026-04-03 13:15:39 +02:00
parent d5179e80b5
commit f9b0e83062
8 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
NOS/txt2corpus.sh
View File

@@ -59,8 +59,8 @@ 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
/net/corpora/nlnieuws/namen.sh -x C -s $corpus.data.dz > $corpus.cat.txt
/net/corpora/nlnieuws/namen.sh -x T -s $corpus.data.dz > $corpus.tag.txt
cd ../..
rm -fr out