@inproceedings{noriega-atala-etal-2022-learning,
    title = "Learning Open Domain Multi-hop Search Using Reinforcement Learning",
    author = "Noriega-Atala, Enrique  and
      Surdeanu, Mihai  and
      Morrison, Clayton",
    editor = "Chen, Wenhu  and
      Chen, Xinyun  and
      Chen, Zhiyu  and
      Yao, Ziyu  and
      Yasunaga, Michihiro  and
      Yu, Tao  and
      Zhang, Rui",
    booktitle = "Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)",
    month = jul,
    year = "2022",
    address = "Seattle, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2022.suki-1.4/",
    doi = "10.18653/v1/2022.suki-1.4",
    pages = "26--35",
    abstract = "We propose a method to teach an automated agent to learn how to search for multi-hop paths of relations between entities in an open domain. The method learns a policy for directing existing information retrieval and machine reading resources to focus on relevant regions of a corpus. The approach formulates the learning problem as a Markov decision process with a state representation that encodes the dynamics of the search process and a reward structure that minimizes the number of documents that must be processed while still finding multi-hop paths. We implement the method in an actor-critic reinforcement learning algorithm and evaluate it on a dataset of search problems derived from a subset of English Wikipedia. The algorithm finds a family of policies that succeeds in extracting the desired information while processing fewer documents compared to several baseline heuristic algorithms."
}