Abstract
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.
Cite
CITATION STYLE
Rabinovich, E., Sznajder, B., Spector, A., Shnayderman, I., Aharonov, R., Konopnicki, D., & Slonim, N. (2018). Learning concept abstractness using weak supervision. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 (pp. 4854–4859). Association for Computational Linguistics. https://doi.org/10.18653/v1/d18-1522
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
