Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog

Mayank Mishra, Danish Contractor, Dinesh Raghu


Abstract
Traditional systems designed for task oriented dialog utilize knowledge present only in structured knowledge sources to generate responses. However, relevant information required to generate responses may also reside in unstructured sources, such as documents. Recent state of the art models such as HyKnow (Gao et al., 2021b) and SEKNOW (Gao et al., 2021a) aimed at overcoming these challenges make limiting assumptions about the knowledge sources. For instance, these systems assume that certain types of information, such as a phone number, is always present in a structured knowledge base (KB) while information about aspects such as entrance ticket prices, would always be available in documents. In this paper, we create a modified version of the MutliWOZ-based dataset prepared by (Gao et al., 2021a) to demonstrate how current methods have significant degradation in performance when strict assumptions about the source of information are removed. Then, in line with recent work exploiting pre-trained language models, we fine-tune a BART (Lewiset al., 2020) based model using prompts (Brown et al., 2020; Sun et al., 2021) for the tasks of querying knowledge sources, as well as, for response generation, without makingassumptions about the information present in each knowledge source. Through a series of experiments, we demonstrate that our model is robust to perturbations to knowledge modality (source of information), and that it can fuse information from structured as well as unstructured knowledge to generate responses.
Anthology ID:
2023.findings-eacl.132
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1778–1787
Language:
URL:
https://aclanthology.org/2023.findings-eacl.132
DOI:
10.18653/v1/2023.findings-eacl.132
Bibkey:
Cite (ACL):
Mayank Mishra, Danish Contractor, and Dinesh Raghu. 2023. Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1778–1787, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog (Mishra et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.findings-eacl.132.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-1/2023.findings-eacl.132.mp4