Lance Kaplan

AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks

2018 · arXiv (Cornell University)

Heterogeneous information networks (HINs) are ubiquitous in real-world applications. Due to the heterogeneity in HINs, the typed edges may not fully align with each other. In order to capture the semantic subtlety, we propose the …

Quantifying Classification Uncertainty using Regularized Evidential Neural Networks

2019 · arXiv (Cornell University)

Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class probabilities to minimize risk …

Spherical Text Embedding

2019 · arXiv (Cornell University)

Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word …