Creating a reusable English – Afrikaans parallel corpora for bilingual dictionary construction

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 from texts collected from the South African government and partly from the OPUS corpus. The recall and accuracy of the bilingual dictionary was evaluated based on the statistical data collected. Samples of translations were generated, compiled as questionnaires and then assessed by English – Afrikaans speaking respondents. The results yielded an accuracy of 87.2 percent and a recall of 67.3 percent for the processed dictionary. Our English – Afrikaans parallel corpora can be found at the following address: let.rug.nl