A resource-based Korean morphological annotation system

TL;DR

This paper presents a resource-based system for Korean morphological annotation that directly uses a lexicon, enabling easy updates and accurate linguistic annotation of agglutinative Korean text.

Contribution

It introduces a novel resource-based approach that performs morphological annotation without relying on morphological rules, allowing for flexible updates.

Findings

Accurate morphological annotation achieved

System allows easy updates of language resources

Annotation performed directly with a lexicon

Abstract

We describe a resource-based method of morphological annotation of written Korean text. Korean is an agglutinative language. The output of our system is a graph of morphemes annotated with accurate linguistic information. The language resources used by the system can be easily updated, which allows us-ers to control the evolution of the per-formances of the system. We show that morphological annotation of Korean text can be performed directly with a lexicon of words and without morpho-logical rules.