[default]

thesauruspath = openthesaurus.csv
path2xml = ticketSamples.xml

language = de

[preprocessing]

ents2keep = WORK_OF_ART,ORG,PRODUCT,LOC

custom_words = grüßen,fragen

#lemmatize = True


[topic modeling]

ngrams = (1,2)

min_df = 0
max_df = 1.0
no_below = 20
no_above = 0.5

topicModel = lda

top_topic_words = 5

top_document_labels_per_topic = 2