Zero-shot Learning of Classifiers from Natural Language Quantification

Shashank Srivastava, Igor Labutov, Tom Mitchell


Abstract
Humans can efficiently learn new concepts using language. We present a framework through which a set of explanations of a concept can be used to learn a classifier without access to any labeled examples. We use semantic parsing to map explanations to probabilistic assertions grounded in latent class labels and observed attributes of unlabeled data, and leverage the differential semantics of linguistic quantifiers (e.g., ‘usually’ vs ‘always’) to drive model training. Experiments on three domains show that the learned classifiers outperform previous approaches for learning with limited data, and are comparable with fully supervised classifiers trained from a small number of labeled examples.
Anthology ID:
P18-1029
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
306–316
Language:
URL:
https://aclanthology.org/P18-1029
DOI:
10.18653/v1/P18-1029
Bibkey:
Cite (ACL):
Shashank Srivastava, Igor Labutov, and Tom Mitchell. 2018. Zero-shot Learning of Classifiers from Natural Language Quantification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 306–316, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Zero-shot Learning of Classifiers from Natural Language Quantification (Srivastava et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1029.pdf
Poster:
 P18-1029.Poster.pdf