Learning Concept Abstractness Using Weak Supervision

09/05/2018
by   Ella Rabinovich, et al.
0

We introduce a weakly supervised approach for inferring the property of abstractness of words and expressions in the complete absence of labeled data. Exploiting only minimal linguistic clues and the contextual usage of a concept as manifested in textual data, we train sufficiently powerful classifiers, obtaining high correlation with human labels. The results imply the applicability of this approach to additional properties of concepts, additional languages, and resource-scarce scenarios.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset