Abstract
This study addresses a series of methodological questions that arise when modeling inflectional morphology with Linear Discriminative Learning. Taking the semi-productive German noun system as example, we illustrate how decisions made about the representation of form and meaning influence model performance. We clarify that for modeling frequency effects in learning, it is essential to make use of incremental learning rather than the end-state of learning. We also discuss how the model can be set up to approximate the learning of inflected words in context. In addition, we illustrate how in this approach the wug task can be modeled. The model provides an excellent memory for known words, but appropriately shows more limited performance for unseen data, in line with the semi-productivity of German noun inflection and generalization performance of native German speakers.
Highlights
Computational models of morphology fall into two broad classes
A further possible evaluation metric is to see how well the model performs on words with forms that have not been encountered in the training data
We illustrated the methodological consequences of the many different choices that have to be made when modeling morphological systems within the discriminative lexicon framework, using LDL as modeling engine. We illustrated these choices for the German noun system
Summary
Computational models of morphology fall into two broad classes. The first class addresses the question of how to produce a morphologically complex word given a morphologically related form (often a stem, or an identifier of a stem or lexeme) and a set of inflectional or derivational features. Prominent form-oriented models comprise Analogical Modeling of Language (AML; Skousen, 1989, 2002) and Memory Based Learning (MBL; Daelemans and Van den Bosch, 2005), which are nearest-neighbor classifiers. Input to these models are tables with observations (words) in rows, and factorial predictors and a factorial response in columns. Predictions are based on sets of nearest neighbors, serving as constrained exemplar sets for generalization These models have clarified morphological phenomena ranging from the allomorphy of the Dutch diminutive (Daelemans et al, 1995) to stress assignment in English (Arndt-Lappe, 2011)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
