PulseAugur
中
实时 18:47:08
English(EN) Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$

新的Moose方法增强了OWL 2 EL本体的神经符号学习

研究人员开发了Moose,一种新颖的神经符号学习方法,专为OWL 2 EL配置文件设计,该配置文件用于大型本体,如Gene Ontology和SNOMED CT。与处理命题理论或Datalog的先前方法不同,Moose解决了本体设置中的推理捷径意识问题。该方法将OWL EL TBoxes和ABoxes编译成Sentential Decision Diagrams,实现了可微分的加权模型计数,并通过闭包子句克服了部分监督的表达能力限制。Moose在涉及潜在概念学习的任务中,在MNIST-with-ontology和pizzaiolo数据集上的表现优于现有基线,并提供了OWL EL背景下的首次推理捷径分析。 AI

影响 这项研究通过在复杂的本体结构中实现更复杂اً的概念学习和推理,推动了神经符号AI的发展。

排序理由 该集群描述了一种在学术论文中提出的用于特定类型本体学习的新方法。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的Moose方法增强了OWL 2 EL本体的神经符号学习

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一种在学术论文中提出的用于特定类型本体学习的新方法。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
56 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho, Robert Hoehndorf ·

    Moose:具有推理捷径意识的 $\mathcal{EL}^{++}$ 中的潜在概念学习

    arXiv:2608.12961v1 Announce Type: new Abstract: The OWL 2 EL profile is used in some of the largest production ontologies, including the Gene Ontology and SNOMED CT. Existing neuro-symbolic (NeSy) learning methods accept propositional theories or Datalog, and reasoning-shortcut (…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Moose:具有推理捷径意识的 $\mathcal{EL}^{++}$ 中的潜在概念学习

    The OWL 2 EL profile is used in some of the largest production ontologies, including the Gene Ontology and SNOMED CT. Existing neuro-symbolic (NeSy) learning methods accept propositional theories or Datalog, and reasoning-shortcut (RS) awareness has not been investigated in ontol…