In this recipe, we'll show you how to create a realistic, though not quite state-of-the-art, set of features for CRFs. The features will include normalized tokens, part-of-speech tags, word-shape features, position features, and token prefixes and suffixes. Substitute it for the
SimpleCrfFeatureExtractor in the CRFs for chunking recipe to use it.
The source for this recipe is in
java -cp lingpipe-cookbook.1.0.jar:lib/lingpipe-4.1.0.jar: com.lingpipe.cookbook.chapter5.FancyCrfFeatureExtractor