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 subtask, 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.

本文总结了我们对第一个DialDoc共享任务两个子任务的参与，重点是目标导向的文档基础对话中代理响应预测任务。我们采用限制的有效跨度数据集，利用双仿射分类器模拟跨距，最后使用不同模型的集合。在第二个子任务中，我们采用级联模型，它在预测跨度而不是整个文档时进行响应预测。通过这些方法，我们在两个子任务中相比基线都获得了显着的改进。

面向文档对话的级联跨度提取和响应生成