This is the webpage of our KDD 2020 Paper: Interactive Path Reasoning on Graph for Conversational Recommendation.
Conversational Path Reasoning (CPR) framework introduce graph to address the multi-round conversational recommendation problem. It tackles what item to recommend and what attribute to ask problem through message propagation on the graph.
If you have any question regarding the CPR System, please contact its main author, Mr. Gangyi Zhang: gangyi.zhang@outlook.com
Manual (READ ME!):
https://cpr-conv-rec.github.io/manual.html
Code & Data:
https://github.com/farrecall/SCPR
Our work adopts some designs of EAR. If you want to get more specific content, please refer to EAR.
Resources for paper: Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems.
https://ear-conv-rec.github.io/