From Raw Text to Morphological Rules for Iban Morphological Analyser

摘要

To extend a complete workflow of automatic acquisition of morphological rules for morphological analyser, we propose a semi-automatic workflow for under-resourced language, which is Iban language. The workflow focuses in determining the rules to be used for building Iban morphological analyser without prior knowledge of language-specific morphological rules. This work introduces three main steps in acquiring the rules from the under-resourced language, which are morphological rules extraction, validation of the extracted rules and evaluation of the generated rules. From the proposed workflow, 25 rules were generated from 744 rules candidate. This work has achieved 76% of precision and 99% of recall. We believe the workflow will assist other researchers to build morphological analyser with the validated morphological rules for the under-resourced languages.