@inproceedings{kuwabara-etal-2020-single,
    title = "Single Model Ensemble using Pseudo-Tags and Distinct Vectors",
    author = "Kuwabara, Ryosuke  and
      Suzuki, Jun  and
      Nakayama, Hideki",
    editor = "Jurafsky, Dan  and
      Chai, Joyce  and
      Schluter, Natalie  and
      Tetreault, Joel",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.acl-main.271/",
    doi = "10.18653/v1/2020.acl-main.271",
    pages = "3006--3013",
    abstract = "Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort. In this study, we propose a novel method that replicates the effects of a model ensemble with a single model. Our approach creates K-virtual models within a single parameter space using K-distinct pseudo-tags and K-distinct vectors. Experiments on text classification and sequence labeling tasks on several datasets demonstrate that our method emulates or outperforms a traditional model ensemble with 1/K-times fewer parameters."
}