2015 FromGrouptoIndividualLabelsUsin

• (Kotzias et al., 2015) ⇒ Dimitrios Kotzias, Misha Denil, Nando de Freitas, and Padhraic Smyth. (2015). “From Group to Individual Labels Using Deep Features.” In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2015). ISBN:978-1-4503-3664-2 doi:10.1145/2783258.2783380

Subject Headings:

Cited By

• http://scholar.google.com/scholar?q=%222015%22+From+Group+to+Individual+Labels+Using+Deep+Features
• http://dl.acm.org/citation.cfm?id=2783258.2783380&preflayout=flat#citedby

Quotes

Author Keywords

• Deep learning; learning; multi-instance learning; sentiment analysis; text analysis; unsupervised learning

Abstract

In many classification problems labels are relatively scarce. One context in which this occurs is where we have labels for groups of instances but not for the instances themselves, as in multi-instance learning. Past work on this problem has typically focused on learning classifiers to make predictions at the group level. In this paper we focus on the problem of learning classifiers to make predictions at the instance level. To achieve this we propose a new objective function that encourages smoothness of inferred instance-level labels based on instance-level similarity, while at the same time respecting group-level label constraints. We apply this approach to the problem of predicting labels for sentences given labels for reviews, using a convolutional neural network to infer sentence similarity. The approach is evaluated using three large review data sets from IMDB, Yelp, and Amazon, and we demonstrate the proposed approach is both accurate and scalable compared to various alternatives.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2015 FromGrouptoIndividualLabelsUsin	Padhraic Smyth Dimitrios Kotzias Misha Denil Nando de Freitas			From Group to Individual Labels Using Deep Features				10.1145/2783258.2783380		2015