A common component of language documentation is the compilation of a small dictionary. The method of compilation has changed very little in the last century: most documentarians elicit individual lexical items from a speaker and check the item through both translat
OpenNMT checkpoints of the models (Procedure D) from the paper "Congolese Swahili Machine Translation for Humanitarian Response" published in Africa NLP workshop organized within the 16th Conference of the European Chapter of the Association for Computational Lingu
Positive TCRs significantly improve children’s developmental outcomes, such as social, emotional, re
International audience Lexical development of monolingual (Bassano, 2000, Kern, 2005)
This paper investigates the possibilities in creating a bilingual English – Afrikaans dictionary by building a parallel corpus and using the Uplug tool to process it. The resulting parallel corpus with approximately 400,000 words per language was created partly fro
Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-