Аңдатпа
Named entity recognition is a core task in natural language processing, involving the automatic identification of entities with specific meanings within text, primarily including proper nouns such as personal names, organisation names and place names. This paper focuses on the development of a deep learning-based named entity recognition system, providing a detailed account of the system’s design and implementation process. Chinese and English corpora were collected to construct training and validation datasets. The Chinese data was sourced from the CLUENER dataset and converted into BIO format using a custom Python script. The English dataset was pre-processed and annotated, and separate Chinese and English models were trained using the BiLSTM-CRF model. Corresponding backend interfaces were developed to invoke the respective models and implement the named entity tagging functionality. The system provides features for user login and registration, file selection and upload, switching between Chinese and English annotation modes, Chinese and English text annotation, and the export and saving of results.