@inproceedings{eyal-etal-2019-question,
    title = "Question Answering as an Automatic Evaluation Metric for News Article Summarization",
    author = "Eyal, Matan  and
      Baumel, Tal  and
      Elhadad, Michael",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/N19-1395/",
    doi = "10.18653/v1/N19-1395",
    pages = "3938--3948",
    abstract = "Recent work in the field of automatic summarization and headline generation focuses on maximizing ROUGE scores for various news datasets. We present an alternative, extrinsic, evaluation metric for this task, Answering Performance for Evaluation of Summaries. APES utilizes recent progress in the field of reading-comprehension to quantify the ability of a summary to answer a set of manually created questions regarding central entities in the source article. We first analyze the strength of this metric by comparing it to known manual evaluation metrics. We then present an end-to-end neural abstractive model that maximizes APES, while increasing ROUGE scores to competitive results."
}