1) Machine learning techniques can automatically acquire linguistic knowledge from annotated corpora, but constructing large annotated corpora requires significant resources. 2) Various methods have been developed to improve machine learning performance when training data is limited, such as ensembles, active learning, transfer learning, unsupervised learning, and semi-supervised learning. 3) Experimental results show these techniques can achieve high accuracy using only a small fraction of the fully labeled training examples that would normally be required.