Cascaded Span Extraction and Response Generation for Document-Grounded Dialog
This work addresses the problem of improving agent response accuracy in goal-oriented document-grounded dialogs, though it is incremental as it builds on existing methods for a specific benchmark.
The paper tackled the DialDoc shared task for document-grounded dialog by predicting grounding spans and generating responses, achieving significant improvements over baselines in both subtasks.
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.