Unsupervised learning of agglutinated morphology using nested Pitman-Yor process based morpheme induction algorithm

In this paper we describe a method of morphologically segment highly agglutinating and inflectional languages from the Dravidian family. We use the nested Pitman-Yor process to segment long agglutinated words into their basic components, and use a corpus based morpheme induction algorithm to perform morpheme segmentation. We test our method on two languages, Malayalam and Kannada and compare the results with Morfessor-baseline.