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
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/P18-1029.pdf