@inproceedings{kadlec-etal-2017-knowledge,
    title = "Knowledge Base Completion: Baselines Strike Back",
    author = "Kadlec, Rudolf  and
      Bajgar, Ondrej  and
      Kleindienst, Jan",
    editor = "Blunsom, Phil  and
      Bordes, Antoine  and
      Cho, Kyunghyun  and
      Cohen, Shay  and
      Dyer, Chris  and
      Grefenstette, Edward  and
      Hermann, Karl Moritz  and
      Rimell, Laura  and
      Weston, Jason  and
      Yih, Scott",
    booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W17-2609/",
    doi = "10.18653/v1/W17-2609",
    pages = "69--74",
    abstract = "Many papers have been published on the knowledge base completion task in the past few years. Most of these introduce novel architectures for relation learning that are evaluated on standard datasets like FB15k and WN18. This paper shows that the accuracy of almost all models published on the FB15k can be outperformed by an appropriately tuned baseline {---} our reimplementation of the DistMult model. Our findings cast doubt on the claim that the performance improvements of recent models are due to architectural changes as opposed to hyper-parameter tuning or different training objectives. This should prompt future research to re-consider how the performance of models is evaluated and reported."
}