General toolkit for analyzing text, with a focus on Japanese, Chinese and other languages requiring word or morpheme segmentation. KyTea is able to perform the following types of processing: - Word Segmentation: it can separate an unsegmented text stream into appropriate units (words or morphemes). - Tagging: it can estimate the tags for words such as POS (part of speech) tags. - Pronunciation: it has the ability to estimate the pronunciation of unknown words. While KyTea comes with a default model, if you have your own annotated text, it provides a tool to train your own model.