5 hasil untuk "Feda Negesse"
Menampilkan 1–5 · 0,47 detik · RSS
-
Artikel Jurnal
Classifying Oromo fricatives with machine learning
Using machine learning, this study investigates how segment duration, spectral moments, and DCT coefficients help differentiating singleton from geminate in Oromo fricatives. Eighteen native Oromo speakers from the western dialect produced speech data consisting of the fricatives in an intervocalic…
-
Artikel Jurnal Teks lengkap
Spectral Features of Wolaytta Ejectives
This study analyzes the spectral properties of word-initial and intervocalic ejectives in Wolaytta, an Omotic language of southern Ethiopia. Using tokens embedded in three vowel contexts, we examined mean burst intensity, spectral moments, and vowel perturbation following ejection. Results show…
-
Artikel Jurnal
Small language models efficacy prototyped for Oromo word sense disambiguation
Abstract Word Sense Disambiguation (WSD) is a fundamental issue in Natural Language Processing (NLP), particularly for low-resource languages with minimal annotated content. The substantial inflection, homonymy, and polysemy of Oromo, a morphologically rich Cushitic language spoken in Ethiopia and…
-
Artikel Jurnal
Evaluating adaptation strategies for low resource word sense disambiguation in Oromo using the BERT base multilingual cased model
Abstract The performance of large language models (LLMs) for Oromo Word Sense Disambiguation (WSD) in a low-resource setting is investigated in this work. In addition to zero-shot, few-shot, and comprehensive fine-tuning paradigms, special attention is given to parameter-efficient adaptation…
-
Artikel Jurnal
Metaphorical conceptualisation of happiness in Oromo
Previous linguistic studies have not addressed how happiness is metaphorically expressed in Oromo and thus this study investigates the metaphorical conceptualisation of happiness in the language. The data for the research were collected from an Oromo web corpus which has around five million running…