Changelog

1.0.1

  • evaluation protocol now ranks object and subjects corruptions separately
  • Corruption generation can now use entites from current batch only
  • FB15k-237, WN18RR loaders filter out unseen triples by default
  • Removed some unused arguments
  • Improved documentation
  • Minor bugfixing

1.0.0

  • TransE
  • DistMult
  • ComplEx
  • FB15k, WN18, FB15k-237, WN18RR, YAGO3-10 loaders
  • generic loader for csv files
  • RDF, ntriples loaders
  • Learning to rank evaluation protocol
  • Tensorflow-based negatives generation
  • save/restore capabilities for models
  • pairwise loss
  • nll loss
  • self-adversarial loss
  • absolute margin loss
  • Model selection routine
  • LCWA corruption strategy for training and eval
  • rank, Hits@N, MRR scores functions