paper-with-me

홈 › Papers

Learning Syllogism with Euler Neural-Networks

2020-07-14 · Tiansi Dong, Chengjiang Li, Christian Bauckhage, Juanzi Li, Stefan Wrobel, Armin B. Cremers

Traditional neural networks represent everything as a vector, and are able to approximate a subset of logical reasoning to a certain degree. As basic logic relations are better represented by topological relations between regions, we propose a novel neural network that represents everything as a ball and is able to learn topological configuration as an Euler diagram. So comes the name Euler Neural-Network (ENN). The central vector of a ball is a vector that can inherit representation power of traditional neural network. ENN distinguishes four spatial statuses between balls, namely, being disconnected, being partially overlapped, being part of, being inverse part of. Within each status, ideal values are defined for efficient reasoning. A novel back-propagation algorithm with six Rectified Spatial Units (ReSU) can optimize an Euler diagram representing logical premises, from which logical conclusion can be deduced. In contrast to traditional neural network, ENN can precisely represent all 24 different structures of Syllogism. Two large datasets are created: one extracted from WordNet-3.0 covers all types of Syllogism reasoning, the other extracted all family relations from DBpedia. Experiment results approve the superior power of ENN in logical representation and reasoning. Datasets and source code are available upon request.

📄 PDF Abstract BibTeX arXiv:2007.07320

Code (0)

등록된 구현이 없습니다.

Tasks

Logical Reasoning

Similar Papers 제목 키워드 기반

Abstract Diagrammatic Reasoning with Multiplex Graph Networks

2020-06-19 · ICLR 2020 1 · Duo Wang, Mateja Jamnik, Pietro Lio

Abstract reasoning, particularly in the visual domain, is a complex human ability, but it remains a challenging problem for artificial neural learning systems. In this work we propose MXGNet, a multilayer graph neural ne…

Graph Neural NetworkVisual Reasoning

Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism

2024-06-26 · Shi Zong, Jimmy Lin

There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this pape…

Logical Reasoning

Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction

2023-07-17 · Cong Jiang, Xiaolei Yang

Legal syllogism is a form of deductive reasoning commonly used by legal professionals to analyze cases. In this paper, we propose legal syllogism prompting (LoT), a simple prompting method to teach large language models …

Articles

On the analysis of set-based fuzzy quantified reasoning using classical syllogistics

2014-11-27 · M. Pereira-Fariña, F. Díaz-Hermida, A. Bugarín

Syllogism is a type of deductive reasoning involving quantified statements. The syllogistic reasoning scheme in the classical Aristotelian framework involves three crisp term sets and four linguistic quantifiers, for whi…

valid

Exploring Reasoning Biases in Large Language Models Through Syllogism: Insights from the NeuBAROCO Dataset

2024-08-08 · Kentaro Ozeki, Risako Ando, Takanobu Morishita, Hirohiko Abe 외

This paper explores the question of how accurately current large language models can perform logical reasoning in natural language, with an emphasis on whether these models exhibit reasoning biases similar to humans. Spe…

Logical Reasoning