Chinese Data Extraction and Named Entity Recognition

Extracting effective information from a large amount of Chinese text data is an important task for data analysis in the era of big data. The key to extracting information is whether it can quickly identify named entities in Chinese text. This paper analyzes the structure of text data about news text and specialized medical text, propose IDCNN-BiLSTM-CRF (Iterated Dilated Convolutions-Bidirectional Long Short Memory Network-Condition Random Field) model. In this paper, medical text data is processed by analyzing the structure of the public news dataset. This paper analyzes the structure of public news datasets to process special medical text data, and uses public news datasets and special medical text datasets to compare and analyze the model proposed in this paper and the BiLSTM-CRF model to verify the recognition result.