@InProceedings{srivastava-labutov-mitchell:2017:EMNLP2017,
  author    = {Srivastava, Shashank  and  Labutov, Igor  and  Mitchell, Tom},
  title     = {Joint Concept Learning and Semantic Parsing from Natural Language Explanations},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1527--1536},
  abstract  = {Natural language constitutes a predominant medium for much of human learning
	and pedagogy. We consider the problem of concept learning from natural language
	explanations, and a small number of labeled examples of the concept. For
	example, in learning the concept of a phishing email, one might say `this is a
	phishing email because it asks for your bank account number'. Solving this
	problem involves both learning to interpret open ended natural language
	statements, and learning the concept itself. We present a joint model for (1)
	language interpretation (semantic parsing) and (2) concept learning
	(classification) that does not require labeling statements with logical forms.
	Instead, the model prefers discriminative interpretations of statements in
	context of observable features of the data as a weak signal for parsing. On a
	dataset of email-related concepts, our approach yields across-the-board
	improvements in classification performance, with a 30% relative improvement in
	F1 score over competitive methods in the low data regime.},
  url       = {https://www.aclweb.org/anthology/D17-1161}
}