sastiahendriwibowo-web/rejang-rule-based-stemming

Morphology-aware rule-based stemming framework for the Rejang low-resource language. # Rejang Morphology-Aware Stemmer This repository contains the dataset, lexicon resources, and experimental materials for the paper: "Character-Level Morphology-Aware Rule-Based Stemming for Rejang Low-Resource Language" ## Contents - Morphological stemming dataset - Rejang root-word lexicon - Document evaluation samples - Experimental resources ## Dataset Statistics | Category | Total | |---|---| | Prefix | 3250 | | Suffix | 2180 | | Infix | 1120 | | Confix | 2450 | Total entries: 9000 words. ## Files - `rejang_morphology_dataset.csv` - `rejang_lexicon.csv` - `rejang_document_evaluation.csv` - `rejang_stemming_dataset_package.xlsx` ## License MIT License ## Citation If you use this dataset, please cite the corresponding paper.