@inproceedings{mao-etal-2018-end,
    title = "End-to-End Reinforcement Learning for Automatic Taxonomy Induction",
    author = "Mao, Yuning  and
      Ren, Xiang  and
      Shen, Jiaming  and
      Gu, Xiaotao  and
      Han, Jiawei",
    editor = "Gurevych, Iryna  and
      Miyao, Yusuke",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/P18-1229/",
    doi = "10.18653/v1/P18-1229",
    pages = "2462--2472",
    abstract = "We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. While prior methods treat the problem as a two-phase task (\textit{i.e.},, detecting hypernymy pairs followed by organizing these pairs into a tree-structured hierarchy), we argue that such two-phase methods may suffer from error propagation, and cannot effectively optimize metrics that capture the holistic structure of a taxonomy. In our approach, the representations of term pairs are learned using multiple sources of information and used to determine \textit{which} term to select and \textit{where} to place it on the taxonomy via a policy network. All components are trained in an end-to-end manner with cumulative rewards, measured by a holistic tree metric over the training taxonomies. Experiments on two public datasets of different domains show that our approach outperforms prior state-of-the-art taxonomy induction methods up to 19.6{\%} on ancestor F1."
}