@inproceedings{peng-etal-2017-maximum,
    title = "Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision",
    author = "Peng, Haoruo  and
      Chang, Ming-Wei  and
      Yih, Wen-tau",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/D17-1252/",
    doi = "10.18653/v1/D17-1252",
    pages = "2368--2378",
    abstract = "Neural networks have achieved state-of-the-art performance on several structured-output prediction tasks, trained in a fully supervised fashion. However, annotated examples in structured domains are often costly to obtain, which thus limits the applications of neural networks. In this work, we propose Maximum Margin Reward Networks, a neural network-based framework that aims to learn from both explicit (full structures) and implicit supervision signals (delayed feedback on the correctness of the predicted structure). On named entity recognition and semantic parsing, our model outperforms previous systems on the benchmark datasets, CoNLL-2003 and WebQuestionsSP."
}