Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph
arXiv:2104.14899
Abstract
Conversational Recommender Systems (CRSs) in E-commerce platforms aim to recommend items to users via multiple conversational interactions. Click-through rate (CTR) prediction models are commonly used for ranking candidate items. However, most CRSs are suffer from the problem of data scarcity and sparseness. To address this issue, we propose a novel knowledge-enhanced deep cross network (K-DCN), a two-step (pretrain and fine-tune) CTR prediction model to recommend items. We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively.To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN.In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended.We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.
arXiv commentPaper is accepted by ICDE2021 industry track
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
- GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
- Can a Chatbot Determine My Diet?: Addressing Challenges of Chatbot Application for Meal Recommendation