2 papers
cs.IR2022
How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation
Hejie Cui, Jiaying Lu, Yao Ge +1
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…
cs.CL2021
Evaluation of Unsupervised Entity and Event Salience Estimation
Jiaying Lu, Jinho D. Choi
Salience Estimation aims to predict term importance in documents. Due to few existing human-annotated datasets and the subjective notion of salience, previous studies typically gen…