Improving part-of-speech tagging in Amharic language using deep neural network

To date, several POS taggers have been introduced to facilitate the success of semantic analysis for different languages. However, task tagging becomes a bit intricate in morphologically complex languages, like Amharic. In this paper, we evaluated models such as bidirectional long short term memory, convolutional neural network combination with and conditional random field Amharic tagging. Various features, both language-dependent -independent, explored model. Besides, word-level character-level features are analyzed deep models. A is utilized encoding at word character level. Each model's performance has on dataset that contained 321 K tokens manually tagged 31 tags. Lastly, best obtained by an end-to-end model, memory field, 97.23% accuracy. This highest accuracy competent contemporary currently existing