210 likes | 380 Views
C onceptNet - a pratical commonsense reasoning tool-kit. H L iu and P Singh MIT Media Lab Speaker: Yi-Ching(Janet) Huang. I ntroduction. ConceptNet Freely available commonsense knowledge base Natual-language-processing tool-kit
E N D
ConceptNet - a pratical commonsense reasoning tool-kit H Liu and P Singh MIT Media Lab Speaker: Yi-Ching(Janet) Huang
Introduction • ConceptNet • Freely available commonsense knowledge base • Natual-language-processing tool-kit • It supports many practical textual-reasoning tasks over real-world documents
Outline • Comparison of ConceptNet, Cyc, and WordNet • History, Construction and Structure • Various contextual reasoning tasks • Quantitative and Qualitative Analysis • Conclusion
CRIS/ OMCSNet Cyc OMCS ConceptNet History of ConceptNet 1984 2000 2002 2004
Building ConceptNet • 3 phases • Extraction phase • Extract from OMCS corpus • English sentence -> binary-relation assertion • Normalization phase • Relaxation phase • Produce “inferred assertion” • Improve the connectivity of the network
Structure of the ConceptNet knowledge base • 1.6 million assertions (1.25 million are k-lines) • twenty relation-types
Practical commonsense reasoning • An integrated natural-language-processing engine • MontyLingua • Text document --> VSOO frames • Reasoning capabilities • Node-level reasoning • Document-level reasoning
Node-level reasoning • Contextual neighborhoods • Spreading activation • Analogy-making • Projection
Document-level reasoning • Topic-gisting • Disambiguation and classification • Novel-concept identification • Affect sensing
Characteristics and quality • ConceptNet’s reasoning abilities hinge largely on the quality of its knowledge
Characteristics of the KB • The histogram of nodal word-lengths 70%
Characteristic of the KB • Average frequency an assertion is uttered of inferred 90% uttered
Characteristics of the KB • The connectivity of nodes in ConceptNet by measuring nodal edge-density
Quality of the knowledge • Two dimensions of quality of ConceptNet, rated by human judges
Applications of ConceptNet Commonsense Investing ARIA OMAdventure AAA GOOSE Commonsense Predictive Text Entry LifeNet GloBuddy Metafor Emotus Ponens MAKEBELIEVE Overhear SAM Bubble Lexicon What Would They Think?
Commonsense ARIA • Analyize E-mail’s content and suggest the related photos
Conclusion • ConceptNet is presently the largest freely commonsense database • Support many practical textual-reasoning tasks • Goodness • Easy to use • Simple structure of WordNet • Good for practical commonsense reasoning