# Morphological Analysis for the Maltese Language: The Challenges of a Hybrid System

## TL;DR

This paper investigates the challenges of Maltese's hybrid morphological system on machine learning tasks, analyzing concatenative and non-concatenative processes through datasets and labelling experiments.

## Contribution

It provides a detailed analysis of how Maltese's hybrid morphology affects machine learning performance in labelling and clustering tasks, highlighting differences between concatenative and non-concatenative systems.

## Key findings

- Performance varies between concatenative and non-concatenative clusters
- Evaluation on unseen and gold standard datasets reveals system-specific challenges
- Morphological labelling accuracy differs across the two morphological processes

## Abstract

Maltese is a morphologically rich language with a hybrid morphological system which features both concatenative and non-concatenative processes. This paper analyses the impact of this hybridity on the performance of machine learning techniques for morphological labelling and clustering. In particular, we analyse a dataset of morphologically related word clusters to evaluate the difference in results for concatenative and nonconcatenative clusters. We also describe research carried out in morphological labelling, with a particular focus on the verb category. Two evaluations were carried out, one using an unseen dataset, and another one using a gold standard dataset which was manually labelled. The gold standard dataset was split into concatenative and non-concatenative to analyse the difference in results between the two morphological systems.