Meituan Knowledge Graph Group's Six Papers Accepted at CIKM 2020

Meituan's search and NLP department announced that six papers from its knowledge graph team were accepted at the top-tier international conference CIKM 2020, covering areas such as knowledge graphs, BERT-based ranking, multi-modal recommendation, sequential recommendation, conversational recommendation, and graph embedding for personalized product search.

The papers include: Query-aware Tip Generation for Vertical Search; TABLE: A Task-Adaptive BERT-based Listwise Ranking Model for Document Retrieval; Multi-Modal Knowledge Graphs for Recommender Systems; S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization; Leveraging Historical Interaction Data for Improving Conversational Recommender System; and Structural relationship representation learning with graph embedding for personalized product search.

These works resulted from collaborations with universities including Xi'an Jiaotong University, University of Chinese Academy of Sciences, Electronic Science and Technology University, Renmin University of China, Xidian University, Nanyang Technological University, and others. Most of the proposed methods have already been deployed in Meituan's search, recommendation, and product search scenarios, delivering measurable business improvements.

The collection demonstrates Meituan's commitment to integrating academic research with engineering practice, advancing technologies such as knowledge graph construction, pre-trained language models, and graph neural networks for real-world applications.