2009 · 76 citations · 31 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingLanguage ModelingLanguage ModelsNatural Language UnderstandingSemantic Role LabelingSemantic RolesSemi-supervised LearningError ReductionPropbank AnnotationRole LabelsSemantic Role AnnotationSemantic Role Labeling EvaluationSemi-supervised ModelsTrainingTraining Error Reduction
Semantic Role Labeling (SRL) has proved to be a valuable tool for performing automatic analysis of natural language texts. Currently however, most systems rely on a large training set, which is manually annotated, an effort that needs to be repeated whenever different languages or a different set of semantic roles is used in a certain application. A possible solution for this problem is semi-supervised learning, where a small set of training examples is automatically expanded using unlabeled texts. We present the Latent Words Language Model, which is a language model that learns word similarities from unlabeled texts. We use these similarities for different semi-supervised SRL methods as additional features or to automatically expand a small training set. We evaluate the methods on the PropBank dataset and find that for small training sizes our best performing system achieves an error reduction of 33.27% F1-measure compared to a state-of-the-art supervised baseline.
31
Zellig S. Harris · WORD · 1954 · 4.7K citations
Semi-Supervised Learning Literature Survey
Xiaojin Zhu · Minds at UW (University of Wisconsin) · 2005 · 3.9K citations · Full text
Class-based n -gram models of natural language
Peter F. Brown, P.V. deSouza, Robert L. Mercer et al. · 1992 · 2.9K citations
Language Studies, Computer Science, Computational Linguistics +15