A Mathematical Framework, a Taxonomy of Modeling Paradigms, and a Suite of Learning Techniques for Neural-Symbolic Systems

1 code implementation • 12 Jul 2024 • Charles Dickens, Connor Pryor, Changyu Gao, Alon Albalak, Eriq Augustine, William Wang, Stephen Wright, Lise Getoor

There is a pressing need for a unifying theory to illuminate the commonalities and differences in approaches and enable further progress.

Image Classification Question Answering

Emotion Recognition in Conversation using Probabilistic Soft Logic

no code implementations • 14 Jul 2022 • Eriq Augustine, Pegah Jandaghi, Alon Albalak, Connor Pryor, Charles Dickens, William Wang, Lise Getoor

Creating agents that can both appropriately respond to conversations and understand complex human linguistic tendencies and social cues has been a long standing challenge in the NLP community.

Emotion Recognition in Conversation Logical Reasoning +2

NeuPSL: Neural Probabilistic Soft Logic

1 code implementation • 27 May 2022 • Connor Pryor, Charles Dickens, Eriq Augustine, Alon Albalak, William Wang, Lise Getoor

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.

Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short

1 code implementation • EMNLP 2017 • Jay Pujara, Eriq Augustine, Lise Getoor

Knowledge graph (KG) embedding techniques use structured relationships between entities to learn low-dimensional representations of entities and relations.

Knowledge Graph Embeddings Knowledge Graphs +1