A named entity recognition method for Chinese aviation accident investigation reports based on prescriptive data augmentation and fine-weighted voting

Key Points

• Named entity recognition accuracy improves with prescriptive data augmentation methods, enhancing detection rates.
• The method achieved an accuracy rate of 92.5% in recognizing key aviation accident entities during trials.
• Assessment using fine-weighted voting techniques was employed to refine the recognition process for various data sets.
• This approach highlights the potential for more reliable investigations into aviation accidents, ensuring crucial data is not overlooked.