Zheng Li

ORCID: 0009-0006-4523-7652
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Semantic Web and Ontologies
  • Advanced Graph Neural Networks
  • Machine Learning in Healthcare
  • Recommender Systems and Techniques
  • Natural Language Processing Techniques
  • Artificial Intelligence in Healthcare and Education

Amazon (United States)
2023-2024

Applications of large-scale knowledge graphs in the e-commerce platforms can improve shopping experience for their customers. While existing (KGs) integrate a large volume concepts or product attributes, they fail to discover user intentions, leaving gap with how people think, behave, and interact surrounding world. In this work, we present COSMO, scalable system mine user-centric commonsense from massive behaviors construct industry-scale empower diverse online services. particular,...

10.1145/3626246.3653398 article EN 2024-05-23

Understanding user intentions is essential for improving product recommendations, navigation suggestions, and query reformulations. However, can be intricate, involving multiple sessions attribute requirements connected by logical operators such as And, Or, Not. For instance, a may search Nike or Adidas running shoes across various sessions, with preference purple. In another example, have purchased mattress in previous session now looking matching bed frame without intending to buy...

10.1145/3637528.3671808 article EN Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2024-08-24

A complex logic query in a knowledge graph refers to expressed form that conveys meaning, such as where did the Canadian Turing award winner graduate from? Knowledge reasoning-based applications, dialogue systems and interactive search engines, rely on ability answer queries fundamental task. In most graphs, edges are typically used either describe relationships between entities or their associated attribute values. An value can be categorical numerical format, dates, years, sizes, etc....

10.1145/3580305.3599399 article EN Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2023-08-04
Coming Soon ...