Learning Concept Abstractness Using Weak Supervision
This work addresses a resource-scarce scenario in natural language processing by enabling abstractness classification without manual annotation.
The authors tackled the problem of inferring word abstractness without labeled data using weak supervision and contextual clues, achieving high correlation with human labels.
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.