Sciweavers

Share
SIGIR
2008
ACM

Learning from labeled features using generalized expectation criteria

9 years 3 months ago
Learning from labeled features using generalized expectation criteria
It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domain knowledge in the form of affinities between input features and classes. For example, in a baseball vs. hockey text classification problem, even without any labeled data, we know that the presence of the word puck is a strong indicator of hockey. We refer to this type of domain knowledge as a labeled feature. In this paper, we propose a method for training discriminative probabilistic models with labeled features and unlabeled instances. Unlike previous approaches that use labeled features to create labeled pseudo-instances, we use labeled features directly to constrain the model's predictions on unlabeled instances. We express these soft constraints using generalized expectation (GE) criteria -terms in a parameter estimation objective function that express preferences on values of a model expectation. ...
Gregory Druck, Gideon S. Mann, Andrew McCallum
Added 15 Dec 2010
Updated 15 Dec 2010
Type Journal
Year 2008
Where SIGIR
Authors Gregory Druck, Gideon S. Mann, Andrew McCallum
Comments (0)
books