engleski

Guessing the Correct Inflectional Paradigm of Unknown Croatian Words

A real-life morphological analyzer must be able to handle properly the out-of-vocabulary words. We address the task of guessing the correct inflectional paradigm of unknown Croatian words. We frame this as a supervised machine learning problem: we train a model for deciding whether a candidate lemma-paradigm pair is correct based on a number of string- and corpus-based features. Our aim is to examine the machine learning aspect of the problem: we analyze the features and evaluate the classification accuracy using different feature subsets. We show that satisfactory level of accuracy (92%) can be achieved with SVM using a combination of string- and corpus-based features. We discuss a number of possible directions for future research.

Morfološka analiza; strojno učenje

nije evidentirano