# Natlog: a Lightweight Logic Programming Language with a Neuro-symbolic Touch

arXiv: https://arxiv.org/abs/2109.08291 · HTML: https://mlsanity.com/paper/2109.08291/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 17 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective](https://mlsanity.com/paper/2003.00330/) (2020)
- [From Statistical Relational to Neuro-Symbolic Artificial Intelligence](https://mlsanity.com/paper/2003.08316/) (2020)
- [Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases](https://mlsanity.com/paper/2102.11965/) (2021)
- [eclingo: A solver for Epistemic Logic Programs](https://mlsanity.com/paper/2008.02018/) (2020)

## Built on by (most cited first, 5 of 5)

- [Neuro-Symbolic AI: Explainability, Challenges, and Future Trends](https://mlsanity.com/paper/2411.04383/) (2024)
- [Full Automation of Goal-driven LLM Dialog Threads with And-Or Recursors and Refiner Oracles](https://mlsanity.com/paper/2306.14077/) (2023)
- [A Gaze into the Internal Logic of Graph Neural Networks, with Logic](https://mlsanity.com/paper/2208.03093/) (2022)
- [Natlog: Embedding Logic Programming into the Python Deep-Learning Ecosystem](https://mlsanity.com/paper/2308.15890/) (2023)
- [Bridging the Gap: Representation Spaces in Neuro-Symbolic AI](https://mlsanity.com/paper/2411.04393/) (2024)

## Abstract (arXiv)

We introduce Natlog, a lightweight Logic Programming language, sharing Prolog's unification-driven execution model, but with a simplified syntax and semantics. Our proof-of-concept Natlog implementation is tightly embedded in the Python-based deep-learning ecosystem with focus on content-driven indexing of ground term datasets. As an overriding of our symbolic indexing algorithm, the same function can be delegated to a neural network, serving ground facts to Natlog's resolution engine. Our open-source implementation is available as a Python package at https://pypi.org/project/natlog/ .