About Lore

Lore is a system for learning general world knowledge – especially commonsense knowledge – from text. It produces formulas in Episodic Logic that are suitable for inference.

Publications

The following publications are related to the creation and evaluation of Lore. See also previous work on Knext.

Jonathan Gordon and Lenhart Schubert: Using Textual Patterns to Learn Expected Event Frequencies. Proceedings of the NAACL 2012 Workshop on Automatic Knowledge Base Construction and Web-Scale Knowledge Extraction (AKBC-WEKEX 2012).
Jonathan Gordon and Lenhart Schubert: Discovering Commonsense Entailment Rules Implicit in Sentences. Proceedings of the EMNLP 2011 Workshop on Textual Entailment (TextInfer 2011).
Jonathan Gordon and Lenhart K. Schubert: Quantificational Sharpening of Commonsense Knowledge. Proceedngs of the AAAI 2010 Fall Symposium on Commonsense Knowledge.

Acknowledgement

This work is currently supported by

NSF IIS-0916599: General Knowledge Bootstrapping from Text
Subcontract FY10-01-0297 under ONR STTR N00014-10-M-0297

It has previously been supported under grants

NSF IIS-0082928: Mining Text for General World Knowledge, 2000–2003
NSF IIS-0328849: Deriving General World Knowledge from Texts by Abstraction of Logical Forms, 2003–2006
NSF IIS-0535105: Knowledge Representation and Reasoning Mechanisms for Explicitly Self-Aware Communicative Agents, 2006–2009
NSF IIS-1016735: Adapting a Natural Logic Reasoning Platform to the Task of Entailment Inference, 2010–2012