论文信息 - Exploiting Ontology Structures and Unlabeled Data for Learning

Exploiting Ontology Structures and Unlabeled Data for Learning

We present and analyze a theoretical model designed to understand and explain the effectiveness of ontologies for learning multiple related tasks from primarily unlabeled data. We present both information-theoretic results as well as efficient algorithms. We show in this model that an ontology, which specifies the relationships between multiple outputs, in some cases is sufficient to completely learn a classification using a large unlabeled data source.

[1] Avrim Blum,et al. The Bottleneck , 2021, Monopsony Capitalism.

[2] Pierre Isabelle,et al. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics , 2002, ACL 2002.

[3] Steven P. Abney,et al. Bootstrapping , 2002, ACL.

[4] Maria-Florina Balcan,et al. A PAC-Style Model for Learning from Labeled and Unlabeled Data , 2005, COLT.

[5] Sham M. Kakade,et al. An Information Theoretic Framework for Multi-view Learning , 2008, COLT.

[6] Claudio Gentile,et al. Linear Algorithms for Online Multitask Classification , 2010, COLT.

[7] Xiaojin Zhu,et al. Introduction to Semi-Supervised Learning , 2009, Synthesis Lectures on Artificial Intelligence and Machine Learning.

[8] Estevam R. Hruschka,et al. Coupled semi-supervised learning for information extraction , 2010, WSDM '10.

[9] Estevam R. Hruschka,et al. Toward an Architecture for Never-Ending Language Learning , 2010, AAAI.

[10] Jingrui He,et al. A Graphbased Framework for Multi-Task Multi-View Learning , 2011, ICML.

[11] Estevam R. Hruschka,et al. Discovering Relations between Noun Categories , 2011, EMNLP.

[12] Estevam R. Hruschka,et al. Coupled Bayesian Sets Algorithm for Semi-supervised Learning and Information Extraction , 2012, ECML/PKDD.