CroMo - Morphological Analysis for Standard Croatian and its Synchronic and Diachronic Dialects and Variants

Abstract

CroMo is a finite state transducer that combines three major functionalities into one high-performance monolithic machine for morphological segmentation, annotation, and lemmatization. It is designed to be flexible, extensible, and applicable to any language that allows for purely morphotactic modeling on the lexical level of morphological structure. While it minimizes the development cycle of the morphology, its annotation schema maximizes interoperability by using a direct mapping from the GOLD ontology of linguistic concepts and features. The use of standardized ontology based annototains provides advanced possibilities for a DL-based post-processing of the annotated output.