Skip to content
/ kb2vec Public

Vectorizing knowledge bases for entity linking

Notifications You must be signed in to change notification settings

uhh-lt/kb2vec

Folders and files

NameName
Last commit message
Last commit date

Latest commit

c022501 · Feb 21, 2021
Jun 18, 2018
Dec 16, 2018
Apr 10, 2019
Feb 21, 2021
Mar 25, 2019
May 2, 2018
Jun 24, 2018
Feb 6, 2019
Aug 6, 2018
Dec 16, 2018
Jun 18, 2018
Nov 11, 2018
Apr 8, 2018
Aug 22, 2018
Mar 16, 2018
Apr 25, 2018
Aug 12, 2018
Apr 10, 2019
Jun 28, 2018
Nov 11, 2018
Jul 7, 2018
Jul 3, 2018
Aug 5, 2018
Jul 4, 2018
Jun 24, 2018

Repository files navigation

kb2vec

Vectorizing knowledge bases for entity linking

Installation

pip install -r requirements.txt
python -m nltk.downloader stopwords
python -m nltk.downloader punkt
python -m nltk.downloader averaged_perceptron_tagger

Download the data folder and and unzip it:

wget http://ltdata1.informatik.uni-hamburg.de/kb2vec/data.zip
unzip data.zip

Start the web service:

Entity linking NIF server:

python nif_ws.py

which will run at http://localhost:5000

GERBIL NIF-based evaluation server (from the gerbil directory):

bash start.sh

which will run at http://localhost:1234/gerbil

DBpedia entity linking NIF wrapper (from the gerbil-dbpedia-ws directory):

docker-compose up -d

which will run at http://localhost:8181/spotlight

http://localhost:8181/spotlight http://localhost:5000/random http://localhost:5000/sparse_overlap http://localhost:5000/dense_overlap http://localhost:5000/supertagger