EMNLP Findings2021
KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals
Jun Zhang, Yan Yang, Chencai Chen, Liang He, Zhou Yu
Abstract
Recommendation dialogs require the system to build a social bond with users to gain trust and develop affinity in order to increase the chance of a successful recommendation. It is beneficial to divide up, such conversations with multiple subgoals (such as social chat, question answering, recommendation, etc.), so that the system can retrieve appropriate knowledge with better accuracy under different subgoals. In this paper, we propose a unified framework for common knowledge-based multi-subgoal dialog: knowledge-enhanced multi-subgoal driven recommender system (KERS). We first predict a sequence of subgoals and use them to guide the dialog model to select knowledge from a sub-set of existing knowledge graph. We then propose three new mechanisms to filter noisy knowledge and to enhance the inclusion of cleaned knowledge in the dialog response generation process. Experiments show that our method obtains stateof-the-art results on DuRecDial dataset in both automatic and human evaluation.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
6 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- A Goal Interaction Graph Planning Framework for Conversational Recommendation cites Towards Conversational Recommendation over Multi-Type Dialogs
- A Goal Interaction Graph Planning Framework for Conversational Recommendation cites INSPIRED: Toward Sociable Recommendation Dialog Systems
- Reinforced Target-driven Conversational Promotion cites Towards Conversational Recommendation over Multi-Type Dialogs
- Reinforced Target-driven Conversational Promotion cites Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
- Reinforced Target-driven Conversational Promotion cites Interactive Path Reasoning on Graph for Conversational Recommendation
- Reinforced Target-driven Conversational Promotion cites INSPIRED: Toward Sociable Recommendation Dialog Systems
- Aligning Recommendation and Conversation via Dual Imitation cites Towards Conversational Recommendation over Multi-Type Dialogs
- Aligning Recommendation and Conversation via Dual Imitation cites Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
- Aligning Recommendation and Conversation via Dual Imitation cites Interactive Path Reasoning on Graph for Conversational Recommendation
- Aligning Recommendation and Conversation via Dual Imitation cites INSPIRED: Toward Sociable Recommendation Dialog Systems
- ESPRESSO: An Effective Approach to Passage Retrieval for High-Quality Conversational Recommender Systems cites Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion
Cited by top-tier papers6
- A Goal Interaction Graph Planning Framework for Conversational RecommendationXiaotong Zhang, Xuefang Jia, Han Liu, Xinyue Liu et al.AAAI 2024 · 9 citations
- ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue AgentsZhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao et al.ACL 2025 · 9 citations
- Aligning Recommendation and Conversation via Dual ImitationJinfeng Zhou, Bo Wang, Minlie Huang, Dongming Zhao et al.EMNLP 2022 · 6 citations
- Reinforced Target-driven Conversational PromotionHuy Dao, Lizi Liao, Dung D. Le, Yuxiang NieEMNLP 2023 · 3 citations
- ESPRESSO: An Effective Approach to Passage Retrieval for High-Quality Conversational Recommender SystemsTaeho Kim, Hyeongjun Jang, Juwon Yu, Taeuk Kim et al.AAAI 2025 · 3 citations
Builds on4
- Improving Conversational Recommender Systems via Knowledge Graph based Semantic FusionKun Zhou, Wayne Xin Zhao, Shuqing Bian, Yuanhang Zhou et al.KDD 2020 · 309 citations
- Interactive Path Reasoning on Graph for Conversational RecommendationWenqiang Lei, Gangyi Zhang, Xiangnan He, Yisong Miao et al.KDD 2020 · 158 citations
- Towards Conversational Recommendation over Multi-Type DialogsZeming Liu, Haifeng Wang, Zheng-Yu Niu, Hua Wu et al.ACL 2020 · 157 citations
- INSPIRED: Toward Sociable Recommendation Dialog SystemsShirley Anugrah Hayati, Dongyeop Kang, Qingxiaoyang Zhu, Weiyan Shi et al.EMNLP 2020 · 106 citations
Related papers
- CP-Rec: Contextual Prompting for Conversational Recommender SystemsKeyu Chen, Shiliang SunAAAI 2023 · 8 citations
- Learning to Ask Appropriate Questions in Conversational RecommendationXuhui Ren, Hongzhi Yin, Tong Chen, Hao Wang et al.SIGIR 2021 · 45 citations
- Knowledge Graph Grounded Goal Planning for Open-Domain Conversation GenerationJun Xu, Haifeng Wang, Zhengyu Niu, Hua Wu et al.AAAI 2020 · 69 citations
- Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language ModelsYongwen Ren, Chao Wang, Peng Du, Chuan Qin et al.AAAI 2026
- CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge GraphsJinfeng Zhou, Bo Wang, Ruifang He, Yuexian HouEMNLP 2021 · 42 citations
