Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

Nico Daheim, David Thulke, Christian Dugast, Hermann Ney


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.
Anthology ID:
2021.dialdoc-1.8
Volume:
Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Song Feng, Siva Reddy, Malihe Alikhani, He He, Yangfeng Ji, Mohit Iyyer, Zhou Yu
Venue:
dialdoc
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
57–62
Language:
URL:
https://aclanthology.org/2021.dialdoc-1.8
DOI:
10.18653/v1/2021.dialdoc-1.8
Bibkey:
Cite (ACL):
Nico Daheim, David Thulke, Christian Dugast, and Hermann Ney. 2021. Cascaded Span Extraction and Response Generation for Document-Grounded Dialog. In Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021), pages 57–62, Online. Association for Computational Linguistics.
Cite (Informal):
Cascaded Span Extraction and Response Generation for Document-Grounded Dialog (Daheim et al., dialdoc 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.dialdoc-1.8.pdf
Code
 ndaheim/dialdoc-sharedtask-21
Data
Doc2Dialdoc2dial