Annif-data-Eurovoc / eurovoc-bonsai-en.cfg
juhoinkinen's picture
Upload project(s) * with Annif
b8392a2 verified
Raw
History Blame Contribute Delete
257 Bytes
[eurovoc-bonsai-en]
name = Eurovoc Omikuji Bonsai English
language = en
backend = omikuji
analyzer = simple
vocab = eurovoc
cluster_balanced = False
cluster_k = 100
max_depth = 3
min_df = 8
ngram = 2
limit = 1000
transform = select(title,text),limit(5000)