Generalized expectation criteria for lightly supervised learning
Machine learning has facilitated many recent advances in natural language processing and information extraction. Unfortunately, most machine learning methods rely on costly labeled data, which impedes their application to new problems. Even in the absence of labeled data we often have a wealth of pr...
Main Author: | Druck, Gregory |
---|---|
Language: | ENG |
Published: |
ScholarWorks@UMass Amherst
2011
|
Subjects: | |
Online Access: | https://scholarworks.umass.edu/dissertations/AAI3482615 |
Similar Items
-
Generalized Expectation Criteria for Lightly Supervised Learning
by: Druck, Gregory
Published: (2011) -
Supervised metric learning with generalization guarantees
by: Bellet, Aurélien
Published: (2012) -
Linguistically motivated models for lightly-supervised dependency parsing
by: Naseem, Tahira
Published: (2014) -
Semi-supervised Named Entity Recognition: Learning to recognize 100 entity types with little supervision
by: Nadeau, David
Published: (2013) -
Automatically constructing compiler optimization heuristics using supervised learning
by: Cavazos, John
Published: (2005)