Improving neural machine translation (NMT) models using the back-translations of the monolingual target data (synthetic parallel data) is currently the state-of-the-art approach for training improved translation systems. The quality of the backward …
This paper presents Hausa WordNet (HWN), a lexical resource for Hausa language. The HWN extracts knowledge from a conventional Hausa dictionary and adopts a substructure of English and Hindi WordNet as it groups words based on different categories. …
Words embedding (distributed word vector representations) have become an essential component of many natural language processing (NLP) tasks such as machine translation, sentiment analysis, word analogy, named entity recognition and word similarity. …
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.