@inproceedings{zhao-etal-2017-end,
    title = "An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective",
    author = "Zhao, Jie  and
      Su, Yu  and
      Guan, Ziyu  and
      Sun, Huan",
    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/fix-sig-urls/D17-1131/",
    doi = "10.18653/v1/D17-1131",
    pages = "1276--1282",
    abstract = "Given a question and a set of answer candidates, answer triggering determines whether the candidate set contains any correct answers. If yes, it then outputs a correct one. In contrast to existing pipeline methods which first consider individual candidate answers separately and then make a prediction based on a threshold, we propose an end-to-end deep neural network framework, which is trained by a novel group-level objective function that directly optimizes the answer triggering performance. Our objective function penalizes three potential types of error and allows training the framework in an end-to-end manner. Experimental results on the WikiQA benchmark show that our framework outperforms the state of the arts by a 6.6{\%} absolute gain under F1 measure."
}