Developing and testing syllabification systems for South African Sesotho.
In this article, we describe the development of two syllabification systems for South African Sesotho. First, we implemented a rule-based syllabification system based on the syllabification rules proposed by Guma (An outline structure of Southern Sotho, 2nd edn, Shooter and Shuter Publishers, Pieter...
| Publicado en: | Language Resources & Evaluation Vol. 59; no. 2; pp. 1577 - 1593 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Jun2025
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=185240062&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 185240062 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Jun2025 vid: 59 iid: 2 pid: 237 pub: Springer Nature artinfo: ui: 185240062 10.1007/s10579-024-09770-8 ppf: 1577 ppct: 16 formats: fmt: – @attributes: type: T – @attributes: type: P size: 910KB tig: atl: Developing and testing syllabification systems for South African Sesotho. aug: au: Sibeko, Johannes van Zaanen, Menno affil: https://ror.org/03r1jm528 Linguistics and Applied Linguistics, Nelson Mandela University, Gqeberha, South Africa South African Centre for Digital Language Resources, Potchefstroom, South Africa su: Low-resource languages Loanwords Encyclopedias & dictionaries Orthography & spelling Test systems sug: subj: Low-resource languages Loanwords Encyclopedias & dictionaries Orthography & spelling Test systems keyword: Low-resource language Pattern-based system Rule-based system Sesotho Syllabification ab: In this article, we describe the development of two syllabification systems for South African Sesotho. First, we implemented a rule-based syllabification system based on the syllabification rules proposed by Guma (An outline structure of Southern Sotho, 2nd edn, Shooter and Shuter Publishers, Pietermaritzburg, 1982). The rules describe the location of syllable boundaries based on the location of vowels, consonants, simple and complex nasal consonants, and the lateral l. Second, we used TeX's pattern-based hyphenation system as a syllabification system. This pattern-based system was trained on syllabified words from a dictionary as identified in Chitja (Phatlamantsoe ya Sesotho ya Machaba, Mazenod Publishers, Lesotho, 2010). The syllable boundaries in the words from the dictionary were manually checked and, where needed, adjusted to maintain a consistent orthography. Both systems were evaluated on 13,551 tokens using ten-fold cross-validation (as the pattern-based system requires training data). The rule-based system shows a 99.69% word level accuracy, which indicates that Sesotho syllabification is highly regular. The pattern-based system leads to 78.97% accuracy. This lower score is likely related to the limitations in the placement of boundaries in the TeX system. A qualitative analysis of the results shows some (unresolved) inconsistencies in the dictionary entries, in particular related to the conversion of the Lesotho Sesotho orthography to the South African Sesotho orthography and the handling of loan words. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2025. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|