TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph

Zhitong Yang, Bo Wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

Abstract
Target-oriented dialog aims to reach a global target through multi-turn conversation. The key to the task is the global planning towards the target, which flexibly guides the dialog concerning the context. However, existing target-oriented dialog works take a local and greedy strategy for response generation, where global planning is absent. In this work, we propose global planning for target-oriented dialog on a commonsense knowledge graph (KG). We design a global reinforcement learning with the planned paths to flexibly adjust the local response generation model towards the global target. We also propose a KG-based method to collect target-oriented samples automatically from the chit-chat corpus for model training. Experiments show that our method can reach the target with a higher success rate, fewer turns, and more coherent responses.
Anthology ID:
2022.coling-1.62
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
745–755
Language:
URL:
https://aclanthology.org/2022.coling-1.62
DOI:
Bibkey:
Cite (ACL):
Zhitong Yang, Bo Wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He, and Yuexian Hou. 2022. TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph. In Proceedings of the 29th International Conference on Computational Linguistics, pages 745–755, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph (Yang et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.coling-1.62.pdf
Code
 yyyyyyzt/topkgchat
Data
ConceptNet, ConvAI2, OTTers
PDF Search Code