paper-with-me

홈 › Papers

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

2021-09-17 · Paul Tarau

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/ .

📄 PDF Abstract BibTeX arXiv:2109.08291

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Natlog: Embedding Logic Programming into the Python Deep-Learning Ecosystem

2023-08-30 · Paul Tarau

Driven by expressiveness commonalities of Python and our Python-based embedded logic-based language Natlog, we design high-level interaction patterns between equivalent language constructs and data types on the two sides…

Deep Learning

NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic

2023-07-06 · Zi'ou Zheng, Xiaodan Zhu

Reasoning has been a central topic in artificial intelligence from the beginning. The recent progress made on distributed representation and neural networks continues to improve the state-of-the-art performance of natura…

Natural Language Inference

Monotonicity Marking from Universal Dependency Trees

2021-04-17 · IWCS (ACL) 2021 6 · Zeming Chen, Qiyue Gao

Dependency parsing is a tool widely used in the field of Natural language processing and computational linguistics. However, there is hardly any work that connects dependency parsing to monotonicity, which is an essentia…

Dependency Parsing

Semirings for Probabilistic and Neuro-Symbolic Logic Programming

2024-02-21 · Vincent Derkinderen, Robin Manhaeve, Pedro Zuidberg Dos Martires, Luc De Raedt

The field of probabilistic logic programming (PLP) focuses on integrating probabilistic models into programming languages based on logic. Over the past 30 years, numerous languages and frameworks have been developed for …

Scallop: A Language for Neurosymbolic Programming

2023-04-10 · Ziyang Li, Jiani Huang, Mayur Naik

We present Scallop, a language which combines the benefits of deep learning and logical reasoning. Scallop enables users to write a wide range of neurosymbolic applications and train them in a data- and compute-efficient…

Logical ReasoningNegation