Docalog: Multi-document Dialogue System using Transformer-based Span Retrieval

Sayed Hesam Alavian, Ali Satvaty, Sadra Sabouri, Ehsaneddin Asgari, Hossein Sameti


Abstract
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative answers based on users’ needs. This paper discusses our proposed approach, Docalog, for the DialDoc-22 (MultiDoc2Dial) shared task. Docalog identifies the most relevant knowledge in the associated document, in a multi-document setting. Docalog, is a three-stage pipeline consisting of (1) a document retriever model (DR. TEIT), (2) an answer span prediction model, and (3) an ultimate span picker deciding on the most likely answer span, out of all predicted spans. In the test phase of MultiDoc2Dial 2022, Docalog achieved f1-scores of 36.07% and 28.44% and SacreBLEU scores of 23.70% and 20.52%, respectively on the MDD-SEEN and MDD-UNSEEN folds.
Anthology ID:
2022.dialdoc-1.16
Volume:
Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venues:
ACL | dialdoc
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
142–147
Language:
URL:
https://aclanthology.org/2022.dialdoc-1.16
DOI:
10.18653/v1/2022.dialdoc-1.16
Bibkey:
Cite (ACL):
Sayed Hesam Alavian, Ali Satvaty, Sadra Sabouri, Ehsaneddin Asgari, and Hossein Sameti. 2022. Docalog: Multi-document Dialogue System using Transformer-based Span Retrieval. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 142–147, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Docalog: Multi-document Dialogue System using Transformer-based Span Retrieval (Alavian et al., dialdoc 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.dialdoc-1.16.pdf
Code
 sharif-slpl-nlp/docalog-2022
Data
CoQADoc2DialMultiDoc2DialQuACdoc2dial