Performance analysis of sub-word language modeling for under-resourced languages with rich morphology : case study on Swahili and Amharic This paper investigates the impact on ASR performance of sub-word units for two underresourced african languages with rich morphology (Amharic and Swahili). Two subword units are considered : syllable and morpheme, the latter being obtained in a supervised or...

Performance analysis of sub-word language modeling for under-resourced languages with rich morphology : case study on Swahili and Amharic This paper investigates the impact on ASR performance of sub-word units for two underresourced african languages with rich morphology (Amharic and Swahili). Two subword units are considered : syllable and morpheme, the latter being obtained in a supervised or...

This paper describes a heuristic for morphemeand morphology-learning based on string edit distance. Experiments with a 7,000 word corpus of Swahili, a language with a rich morphology, support the effectiveness of this approach.

Research in machine translation and corpus annotation has greatly benefited from the increasing availability of word-aligned parallel corpora. This paper presents ongoing research on the development and application of the SAWA corpus, a two-million-word parallel corpus English—Swahili. We describe the data collection phase and zero in on the difficulties of finding appropriate and easily access...

Of the several African languages that have become regularly offered at U.S. colleges and universities, Swahili consistently garners the highest enrollments, and is the second most widely taught after Arabic, with the greatest variety of instructional materials compared to its Sub-Saharan African counterparts. According to the Modern Language Association, the number of Swahili-language learners ...

SWATWOL is a computer program which has been designed to analyze morphologically Standard Swahili texts. It is based on Koskenniemi's (1983) already well-known two-level model. A number of applications of this model on various languages exist already. Some of those are very ambitious and almost complete (Koskenniemi 1983; Karlsson 1992), others being still in various stages of development. The ...