Download presentation
Presentation is loading. Please wait.
1
Meaningful Compound Concept Learning?
Wentao Ding
2
任务目标 对于知识库中的类𝐶，组合本体中的原子谓词， 得到𝐶的子类𝑋，要求𝑋存在有意义的自然语言解 释 “NBA Player” [
a owl:Restriction; rdfs:subClassOf dbo:Person owl:onProperty dbo:league owl:hasValue dbr:National_Basketball_Association ]
3
相关任务 Ontology Learning from Text Linked Data Mining
mostly focuses on the automatic or semi-automatic generation of lightweight taxonomies. Linked Data Mining refers to the process of detecting meaningful patterns in RDF graphs. Concept Learning in Description Logics/OWL is a direction of research that aims at learning schema axioms, such as definitions of classes. Knowledge based Natural Language Interpretation? Adj2ER
4
可能的路线 取一个有意义的𝐶 枚举可能在𝐶上组合的原子约束𝐴 生成表述 记𝐶与𝐴组合得到𝑋 尝试生成适合𝑋而不适合𝐶的表述 取满足约束的实例
若成功，记𝑋为有意义的 生成表述 取满足约束的实例 基于模式提取实例的可能描述 分析生成当前约束的表述
5
相关研究 DL-learner Biperpedia Adj2ER
Similar presentations
