An implementation of TransE with tensorflow.
TransE is proposed by Antoine Bordes, Nicolas Usunier and Alberto Garcia-Duran in 2013. The paper title is Translating Embeddings for Modeling Multi-relational Data
The dataset WN18 and FB15k are orginally published by TransE paper and cand be download here
The data used here are from here
to run the model with default parameter setting:
--- 'python3 TransE.py'.
If you run this code using python2 there will be some error because print setting '\t' is not supported by python2.
to change the parameter setting you can use
--- 'python3 TransE.py --help'
to see the optional arguments.
the default setting for testing is testing once with 300 triples after every 10 training iteration