Learning Hebrew roots: Machine learning with linguistic constraints

The morphology of Semitic languages is unique in the sense that the major word-formation mechanism is an inherently non-concatenative process of interdigitation, whereby two morphemes, a root and a pattern, are interwoven. Identifying the root of a given word in a Semitic language is an important task, in some cases a crucial part of morphological analysis. It is also a non-trivial task, which many humans find challenging. We present a machine learning approach to the problem of extracting roots of Hebrew words. Given the large number of potential roots (thousands), we address the problem as one of combining several classifiers, each predicting the value of one of the root's consonants. We show that when these predictors are combined by enforcing some fairly simple linguistics constraints, high accuracy, which compares favorably with human performance on this task, can be achieved.