UGent-T2K at the 2nd DialDoc Shared Task: A Retrieval-Focused Dialog System Grounded in Multiple Documents

Yiwei Jiang, Amir Hadifar, Johannes Deleu, Thomas Demeester, Chris Develder

Abstract
This work presents the contribution from the Text-to-Knowledge team of Ghent University (UGent-T2K) to the MultiDoc2Dial shared task on modeling dialogs grounded in multiple documents. We propose a pipeline system, comprising (1) document retrieval, (2) passage retrieval, and (3) response generation. We engineered these individual components mainly by, for (1)-(2), combining multiple ranking models and adding a final LambdaMART reranker, and, for (3), by adopting a Fusion-in-Decoder (FiD) model. We thus significantly boost the baseline system’s performance (over +10 points for both F1 and SacreBLEU). Further, error analysis reveals two major failure cases, to be addressed in future work: (i) in case of topic shift within the dialog, retrieval often fails to select the correct grounding document(s), and (ii) generation sometimes fails to use the correctly retrieved grounding passage. Our code is released at this link.
Anthology ID:
2022.dialdoc-1.12
Volume:
Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Song Feng, Hui Wan, Caixia Yuan, Han Yu
Venue:
dialdoc
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
115–122
Language:
URL:
https://aclanthology.org/2022.dialdoc-1.12
DOI:
10.18653/v1/2022.dialdoc-1.12
Bibkey:
Cite (ACL):
Yiwei Jiang, Amir Hadifar, Johannes Deleu, Thomas Demeester, and Chris Develder. 2022. UGent-T2K at the 2nd DialDoc Shared Task: A Retrieval-Focused Dialog System Grounded in Multiple Documents. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 115–122, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
UGent-T2K at the 2nd DialDoc Shared Task: A Retrieval-Focused Dialog System Grounded in Multiple Documents (Jiang et al., dialdoc 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2022.dialdoc-1.12.pdf
Data
Doc2Dial, MultiDoc2Dial, doc2dial
PDF Search