Graphs

WN18

WordNet18

Introduced in Translating Embeddings for Modeling Multi-relational Data2012

About this Dataset

The WN18 dataset has 18 relations scraped from WordNet for roughly 41,000 synsets, resulting in 141,442 triplets. It was found out that a large number of the test triplets can be found in the training set with another relation or the inverse relation. Therefore, a new version of the dataset WN18RR has been proposed to address this issue.

Source: http://nlpprogress.com/english/relation_prediction.html

Source: Translating Embeddings for Modeling Multi-relational Data

Dataset Variants

WN18WN18RRWN18 (filtered)

Papers1

Translating Embeddings for Modeling Multi-relational Data

TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.

Dataset Loaders

EDIT

🔥

rusty1s/pytorch_geometric

pytorch

🔥

dmlc/dgl

pytorchtfmxnet

🎯

tensorflow/datasets

tfjax

🔥