Guiding Dialogue Agents to Complex Semantic Targets by Dynamically Completing Knowledge Graph

Yue Tan, Bo Wang, Anqi Liu, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

Abstract
In the target-oriented dialogue, the representation and achievement of targets are two interrelated essential issues. In current approaches, the target is typically supposed to be a single object represented as a word, which makes it relatively easy to achieve the target through dialogue with the help of a knowledge graph (KG). However, when the target has complex semantics, the existing knowledge graph is often incomplete in tracking complex semantic relations. This paper studies target-oriented dialog where the target is a topic sentence. We combine the methods of knowledge retrieval and relationship prediction to construct a context-related dynamic KG. On dynamic KG, we can track the implicit semantic paths in the speaker’s mind that may not exist in the existing KGs. In addition, we also designed a novel metric to evaluate the tracked path automatically. The experimental results show that our method can control the agent more logically and smoothly toward the complex target.
Anthology ID:
2023.findings-acl.407
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6506–6518
Language:
URL:
https://aclanthology.org/2023.findings-acl.407
DOI:
10.18653/v1/2023.findings-acl.407
Bibkey:
Cite (ACL):
Yue Tan, Bo Wang, Anqi Liu, Dongming Zhao, Kun Huang, Ruifang He, and Yuexian Hou. 2023. Guiding Dialogue Agents to Complex Semantic Targets by Dynamically Completing Knowledge Graph. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6506–6518, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Guiding Dialogue Agents to Complex Semantic Targets by Dynamically Completing Knowledge Graph (Tan et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-acl.407.pdf
PDF Search