Skip to content

fnielsen/dasem

Folders and files

NameName
Last commit message
Last commit date

Latest commit

3718e8a · Sep 24, 2020
Sep 24, 2020
May 3, 2019
Mar 3, 2017
Apr 5, 2017
Mar 6, 2017
Sep 20, 2016
Sep 13, 2016
Mar 6, 2017
Nov 2, 2017
May 1, 2020
Feb 23, 2017
Dec 8, 2017
Mar 6, 2017
Mar 3, 2017
Mar 6, 2017

Repository files navigation

Dasem

Danish semantic analysis.

Examples

Get nouns from Dannet and Wiktionary:

from dasem.wiktionary import get_nouns
from dasem.dannet import Dannet

wiktionary_nouns = get_nouns()

dannet = Dannet()
query = "select w.form from words w where w.pos = 'Noun'"
dannet_nouns = set(dannet.db.query(query).form)

nouns = dannet_nouns.union(wiktionary_nouns)

Get similar words based on a word2vec model on the Danish part of the Project Gutenberg corpus:

$ python -m dasem.gutenberg most-similar mand
kvinde
dame
pige
kone
fyr
dreng
præst
profet
hund
person

Get first two sentences from Dannet synsets examples:

$ python -m dasem.dannet get-all-sentences | head -n 2
I september måned var jeg sammen med en dansk gruppe af unge bøsser og lesbiske i Moskva
Til en gruppe på 10 børn i alderen 0-3 år søges pr. 1.3.83 en pædagog 40 timer ugentligt

Reference