MONPA：中文命名實體及斷詞與詞性同步標註系統

有鑑於現今國內外研究繁體中文自然語言處理缺乏合適的斷詞、詞性標註及命名實體辨識的工具，本研究基於BERT模型，搭配CRF提出以多目標命名實體辨識與詞性標註（Multi-Objective NER POS Annotator, MONPA）系統，並以供學術使用授權條款CC BY-NC-SA 4.0 License進行相關安裝套件釋出作業。透過MONPA的釋出，嘉惠我國相關學術研究，俾能加快繁體中文自然語言處理之進展。

In view of the lack of suitable word segmentation, part-of-speech tagging and named entity recognition tools in the traditional Chinese natural language processing. This study is based on the BERT model with CRF to propose a multi-objective named-entity and part-of-speech annotator, which called MONPA. Our work not only propose a method but also release the relevant python package with the CC BY-NC-SA 4.0 License. We firmly believe that this research project can bridge the technical gap between academia and business applications with our innovation, and enable efficient development of traditional Chinese NLP by all entities in order to enhance our level of competitiveness in the world.