@inproceedings{daheim-etal-2021-cascaded,
    title = "Cascaded Span Extraction and Response Generation for Document-Grounded Dialog",
    author = "Daheim, Nico  and
      Thulke, David  and
      Dugast, Christian  and
      Ney, Hermann",
    editor = "Feng, Song  and
      Reddy, Siva  and
      Alikhani, Malihe  and
      He, He  and
      Ji, Yangfeng  and
      Iyyer, Mohit  and
      Yu, Zhou",
    booktitle = "Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.dialdoc-1.8/",
    doi = "10.18653/v1/2021.dialdoc-1.8",
    pages = "57--62",
    abstract = "This paper summarizes our entries to both subtasks of the first DialDoc shared task which focuses on the agent response prediction task in goal-oriented document-grounded dialogs. The task is split into two subtasks: predicting a span in a document that grounds an agent turn and generating an agent response based on a dialog and grounding document. In the first subtask, we restrict the set of valid spans to the ones defined in the dataset, use a biaffine classifier to model spans, and finally use an ensemble of different models. For the second sub-task, we use a cascaded model which grounds the response prediction on the predicted span instead of the full document. With these approaches, we obtain significant improvements in both subtasks compared to the baseline."
}