A Method of Chinese Named Entity Recognition Based on CNN-BILSTM-CRF Model

The main task of naming entity recognition is to identify the person names, location names, organization names, meaningful time, dates and other quantitative phrases and also classifying them into different categories. Yet, there are lots of field terms, meaningful entities, complicated location names and complex name of organizations contained in all kinds of these field terms is the most important mission in digging out the text now. The extraction of Chinese is more difficult than English entities owing to the lack of definite boundary and size characteristics of Chinese words. Therefore, we would train and test the marked corpus which is based on the CNN-BILSTM-CRF neutral network model in order to make good use of CNN to get the presentation character of words and label the words by using BILSTM and CRF. It makes the extraction of entity in the common came true. The experimental results show that the accuracy rate, recall rate and F value that we got in an unaddressed artificial features condition are 98.81%, 90.70% and 91.57% respectively which is better than the results we got by using the method of BILSTM+CRF and conditional random field (CRF).