Lusoga-English Parallel Corpus and Its Application

Language parallel corpora can be used as key resources for cross lingual information processing language research and teaching contrastive linguistics translation studies and bilingual lexicography. Unfortunately parallel corpora are not available for many African languages. In this book we describe the construction of a Lusoga-English parallel corpus that upon which several information processing applications can be realized such as machine translation information retrieval bilingual lexicography Concordancing among others. In this study we specifically contribute a parallel concordancer that uses the Lusoga-English parallel corpus. For corpus construction parallel text collection transformation annotation and mark-up were undertaken. The book thus presents an approach and work flow for a parallel corpora and its application to a concordance tool.