Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

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 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.

Authors 4

1. Nico Daheim Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany

2. David Thulke Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH , Aachen , Germany

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany

3. Christian Dugast Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH , Aachen , Germany

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany

4. Hermann Ney Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH , Aachen , Germany

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany