Eriq Augustine
YOU?
Author Swipe
View article: A Mathematical Framework, a Taxonomy of Modeling Paradigms, and a Suite of Learning Techniques for Neural-Symbolic Systems
A Mathematical Framework, a Taxonomy of Modeling Paradigms, and a Suite of Learning Techniques for Neural-Symbolic Systems Open
The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and symbolic methods. However, each NeSy system differs in fundamental ways. There is a pressing…
View article: NeuPSL: Neural Probabilistic Soft Logic
NeuPSL: Neural Probabilistic Soft Logic Open
In this paper, we introduce Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic (NeSy) framework that unites state-of-the-art symbolic reasoning with the low-level perception of deep neural networks. To model the boundary betw…
View article: A taxonomy of weight learning methods for statistical relational learning
A taxonomy of weight learning methods for statistical relational learning Open
Statistical relational learning (SRL) frameworks are effective at defining probabilistic models over complex relational data. They often use weighted first-order logical rules where the weights of the rules govern probabilistic interaction…
View article: Tandem Inference: An Out-of-Core Streaming Algorithm for Very Large-Scale Relational Inference
Tandem Inference: An Out-of-Core Streaming Algorithm for Very Large-Scale Relational Inference Open
Statistical relational learning (SRL) frameworks allow users to create large, complex graphical models using a compact, rule-based representation. However, these models can quickly become prohibitively large and not fit into machine memory…
View article: Entity Resolution at Large Scale: Benchmarking and Algorithmics
Entity Resolution at Large Scale: Benchmarking and Algorithmics Open
We seek scalable benchmarks for entity resolution problems. Solutions to these problems range from trivial approaches such as string sorting to sophisticated methods such as statistical relational learning. The theoretical and practical co…
View article: Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short
Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short Open
Knowledge graph (KG) embedding techniques use structured relationships between entities to learn low-dimensional representations of entities and relations. One prominent goal of these approaches is to improve the quality of knowledge graph…