Research on Text Fine Grained Information Extraction Method Based on Pre-trained Language Model

In view of the complexity and manual participation in information extraction, an information automatic extraction method based on Part-of-speech Tagging is proposed with aviation service support normative texts. This method is based on a general domain pre-trained language model (PLM) provided by NLP platforms. On the premise of optimizing lexical analysis results and sentences pattern similarity measure, it achieves automatic extraction of information for aviation service support. The extraction results can provide more accurate data support for the guidance of aviation service support. Meanwhile, the information automatic extraction method described in the article can quickly adapt to new knowledge extraction needs and has good adaptability to similar needs in other fields.