How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation. (arXiv:2201.04672v1 [cs.IR])

Graph neural networks (GNNs), as a group of powerful tools for representation
learning on irregular data, have manifested superiority in various downstream
tasks. With unstructured texts represented as concept maps, GNNs can be
exploited for tasks like document retrieval. Intrigued by how can GNNs help
document retrieval, we conduct an empirical study on a large-scale
multi-discipline dataset CORD-19. Results show that instead of the complex
structure-oriented GNNs such as GINs and GATs, our proposed semantics-oriented
graph functions achieve better and …

arxiv case study graph graph neural networks map networks neural networks study