Highlight

NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning

A paper proposing a new approach to question answering using neural language modeling and symbolic reasoning.

Based on

NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning

By Nathaniel Weir, Clark, Peter, Van Durme, BenjaminarXiv (Cornell University)
Read original article →

The authors present NELLIE, a system that combines neural language modeling with symbolic reasoning to answer questions. This approach is grounded in natural language corpora and produces human-interpretable proof trees.

The system outperforms state-of-the-art reasoners while providing knowledge-grounded explanations.

Abstract

The authors present NELLIE, a system that combines neural language modeling with symbolic reasoning to answer questions. This approach is grounded in natural language corpora and produces human-interpretable proof trees. The system outperforms state-of-the-art reasoners while providing knowledge-grounded explanations.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

neuro-symbolic reasoninginference enginequestion answeringgrounded explanationssymbolic reasoningLarge Language ModelsRetrieval & RAGSemantic InteroperabilityAI Agents
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources