Scalable Discriminative Learning for Natural Language Parsing and Translation
Joseph P. Turian, Benjamin Wellington, I. Dan Melamed · The MIT Press eBooks · 2007
Parsing and translating natural languages can be viewed as problems of pre-dicting tree structures. For machine learning approaches to these predictions, the diversity and high dimensionality of the structures involved mandate very large training sets. This paper presents a purely discriminative learning method that scales up well to problems of this size. Its accuracy was at least as good as other comparable methods on a standard parsing task. To our knowledge, it is the first purely discriminative learning algorithm for translation with tree-structured models. Unlike other popular methods, this method does not require a great deal of feature engineering a priori, because it performs feature selec-tion over a compound feature space as it learns. Experiments demonstrate the method’s versatility, accuracy, and efficiency. Relevant software is freely available at