MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs

Yerin Hwang, Yongil Kim, Yunah Jang, Jeesoo Bang, Hyunkyung Bae, Kyomin Jung


Abstract
Despite advancements in on-topic dialogue systems, effectively managing topic shifts within dialogues remains a persistent challenge, largely attributed to the limited availability of training datasets. To address this issue, we propose Multi-Passage to Dialogue (MP2D), a data generation framework that automatically creates conversational question-answering datasets with natural topic transitions. By leveraging the relationships between entities in a knowledge graph, MP2D maps the flow of topics within a dialogue, effectively mirroring the dynamics of human conversation. It retrieves relevant passages corresponding to the topics and transforms them into dialogues through the passage-to-dialogue method. Through quantitative and qualitative experiments, we demonstrate MP2D’s efficacy in generating dialogue with natural topic shifts. Furthermore, this study introduces a novel benchmark for topic shift dialogues, TS-WikiDialog. Utilizing the dataset, we demonstrate that even Large Language Models (LLMs) struggle to handle topic shifts in dialogue effectively, and we showcase the performance improvements of models trained on datasets generated by MP2D across diverse topic shift dialogue tasks.
Anthology ID:
2024.emnlp-main.979
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
17682–17702
Language:
URL:
https://aclanthology.org/2024.emnlp-main.979
DOI:
Bibkey:
Cite (ACL):
Yerin Hwang, Yongil Kim, Yunah Jang, Jeesoo Bang, Hyunkyung Bae, and Kyomin Jung. 2024. MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17682–17702, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs (Hwang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.979.pdf
Software:
 2024.emnlp-main.979.software.zip
Data:
 2024.emnlp-main.979.data.zip