Mkhwanazi, SthembisoMarais, Laurette2024-09-132024-09-132024-02Mkhwanazi, S. & Marais, L. 2024. Generation of segmented isiZulu text. <i>Journal of the Digital Humanities Association of Southern Africa, 5(1).</i> http://hdl.handle.net/10204/137493006-6492https://doi.org/10.55492/dhasa.v5i1.5034http://hdl.handle.net/10204/13749The complex morphology, conjunctive orthography and widespread occurrence of morphophonological alternation in the Nguni languages have given rise to several efforts towards morphological segmentation of tokens of Nguni languages. For supervised methods, annotated data is required, which currently exists as canonically segmented data in the NCHLT corpus and surface segmented data in the Ukwabelana corpus. In this paper, we present a method and segmentation strategy based on a computational grammar for isiZulu. The grammar, which itself has some limitations in processing speed and robustness to unexpected input, is used to create a new set of segmentations for the tokens of the Ukwabelana corpus.FulltextenNguni languagesAgglutinative languagesMorphological segmentationLanguage modelsSegmented isiZulu textGeneration of segmented isiZulu textArticleMkhwanazi, S., & Marais, L. (2024). Generation of segmented isiZulu text. <i>Journal of the Digital Humanities Association of Southern Africa, 5(1)</i>, http://hdl.handle.net/10204/13749Mkhwanazi, Sthembiso, and Laurette Marais "Generation of segmented isiZulu text." <i>Journal of the Digital Humanities Association of Southern Africa, 5(1)</i> (2024) http://hdl.handle.net/10204/13749Mkhwanazi S, Marais L. Generation of segmented isiZulu text. Journal of the Digital Humanities Association of Southern Africa, 5(1). 2024; http://hdl.handle.net/10204/13749.TY - Article AU - Mkhwanazi, Sthembiso AU - Marais, Laurette AB - The complex morphology, conjunctive orthography and widespread occurrence of morphophonological alternation in the Nguni languages have given rise to several efforts towards morphological segmentation of tokens of Nguni languages. For supervised methods, annotated data is required, which currently exists as canonically segmented data in the NCHLT corpus and surface segmented data in the Ukwabelana corpus. In this paper, we present a method and segmentation strategy based on a computational grammar for isiZulu. The grammar, which itself has some limitations in processing speed and robustness to unexpected input, is used to create a new set of segmentations for the tokens of the Ukwabelana corpus. DA - 2024-02 DB - ResearchSpace DP - CSIR J1 - Journal of the Digital Humanities Association of Southern Africa, 5(1) KW - Nguni languages KW - Agglutinative languages KW - Morphological segmentation KW - Language models KW - Segmented isiZulu text LK - https://researchspace.csir.co.za PY - 2024 SM - 3006-6492 T1 - Generation of segmented isiZulu text TI - Generation of segmented isiZulu text UR - http://hdl.handle.net/10204/13749 ER -28061