@inproceedings{liu-etal-2018-learning-actively,
    title = "Learning How to Actively Learn: A Deep Imitation Learning Approach",
    author = "Liu, Ming  and
      Buntine, Wray  and
      Haffari, Gholamreza",
    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/P18-1174/",
    doi = "10.18653/v1/P18-1174",
    pages = "1874--1883",
    abstract = "Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary. We introduce a method that learns an AL {\textquotedblleft}policy{\textquotedblright} using {\textquotedblleft}imitation learning{\textquotedblright} (IL). Our IL-based approach makes use of an efficient and effective {\textquotedblleft}algorithmic expert{\textquotedblright}, which provides the policy learner with good actions in the encountered AL situations. The AL strategy is then learned with a feedforward network, mapping situations to most informative query datapoints. We evaluate our method on two different tasks: text classification and named entity recognition. Experimental results show that our IL-based AL strategy is more effective than strong previous methods using heuristics and reinforcement learning."
}