Hang Gao

Learning with Holographic Reduced Representations

2021 · arXiv (Cornell University)

Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors by associating each vector with an abstract concept, and providing mathematical operations to manipulate vectors as if they were …

LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty

2024 · arXiv (Cornell University)

Named Entity Recognition (NER) serves as a fundamental task in natural language understanding, bearing direct implications for web content analysis, search engines, and information retrieval systems. Fine-tuned NER models exhibit satisfactory performance on standard NER …

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As the embodiment of an outstanding discriminative unsupervised graph representation …