Acquisition of Common Sense Knowledge for Basic Level Concepts
Eduard Barbu · Recent Advances in Natural Language Processing · 2009
Feature norms can be regarded as repositories of common sense knowledge for basic level concepts. We acquire from very large corpora feature-norm-like concept descriptions using a combination of a weakly supervised method and an unsupervised method. The success in identifying the specific properties listed in the feature norms as well as the success in acquiring the classes of properties present in the norms are reported.