Representation Learning of Entities and Documents from Knowledge Base Descriptions
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.


TextEnt is a software to obtain vector representations of entities and documents from Wikipedia.


You can install this software by:

% git clone
% cd textent
% pip install
% pip install -r requirements.txt

Currently, the code is based on Python 2.

Reproducing Experiments

The experimental results presented in the paper can be reproduced by running the commands described below. We conducted experiments using Python 2.7, Ubuntu Linux 16.04, and NVIDIA GTX GPUs.


Please unarchive these files before proceeding to the next step.

Entity Typing experiment:

% python evaluate_entity_typing textent_300d entity_db_20160601.pkl

The dataset used in this experiment is contained in the dataset/entity_typing directory.

Text classification expeiment on the 20 newsgroups dataset:

% python evaluate_text_classification textent_300d entity_db_20160601.pkl --tagme-cache=tagme_cache.pkl -t 20ng

Text classification experiment on the R8 dataset:

% python evaluate_text_classification textent_300d entity_db_20160601.pkl --tagme-cache=tagme_cache.pkl -t r8