Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset
Minjin Kim, Minju Kim, Hana Kim, Beong-woo Kwak, SeongKu Kang, Youngjae Yu, Jinyoung Yeo, Dongha Lee
Abstract
Conversational recommender systems are an emerging area that has garnered increasing interest in the community, especially with the advancements in large language models (LLMs) that enable sophisticated handling of conversational input. Despite the progress, the field still has many aspects left to explore. The currently available public datasets for conversational recommendation lack specific user preferences and explanations for recommendations, hindering high-quality recommendations. To address such challenges, we present a novel conversational recommendation dataset named PEARL, synthesized with persona- and knowledge-augmented LLM simulators. We obtain detailed persona and knowledge from real-world reviews and construct a large-scale dataset with over 57k dialogues. Our experimental results demonstrate that PEARL contains more specific user preferences, show expertise in the target domain, and provides recommendations more relevant to the dialogue context than those in prior datasets. Furthermore, we demonstrate the utility of PEARL by showing that our downstream models outperform baselines in both human and automatic evaluations. We release our dataset and code.- Anthology ID:
- 2024.findings-acl.65
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1105–1120
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.65
- DOI:
- 10.18653/v1/2024.findings-acl.65
- Cite (ACL):
- Minjin Kim, Minju Kim, Hana Kim, Beong-woo Kwak, SeongKu Kang, Youngjae Yu, Jinyoung Yeo, and Dongha Lee. 2024. Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset. In Findings of the Association for Computational Linguistics: ACL 2024, pages 1105–1120, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset (Kim et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/autopr/2024.findings-acl.65.pdf