Related Experiment Video
Updated: Jul 6, 2025
04:48
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
Published on: July 5, 2024
405
Named entity recognition in aerospace based on multi-feature fusion transformer.
Jing Chu1, Yumeng Liu1, Qi Yue1
1School of Automation, Xi'an University of Posts & Telecommunications, 618 West Chang'an Street, Chang'an District, Xi'an, 710121, China.
Scientific Reports
|January 9, 2024
Summary
This study introduces a new Multi-Feature Fusion Transformer (MFT) model for Named Entity Recognition (NER) in aerospace. The MFT model achieves an 86.10% F1 score on a custom Chinese aerospace dataset.
Area of Science:
- Artificial Intelligence
- Aerospace Engineering
- Natural Language Processing
Background:
- The integration of artificial intelligence (AI) and aerospace is a significant future trend.
- Named Entity Recognition (NER) is crucial for extracting knowledge from extensive aerospace data.
- Existing NER models may not fully capture the nuances of specialized aerospace terminology.
Purpose of the Study:
- To develop a high-performance NER model tailored for the aerospace domain.
- To create a comprehensive Chinese aerospace entity recognition dataset.
- To enhance semantic understanding by fusing multi-modal features within the NER model.
Main Methods:
- Development of a novel Multi-Feature Fusion Transformer (MFT) model.
- Fusion of word and radical features to enrich semantic information.
- Utilization of a double Feed-forward Neural Network to improve model performance.
- Training the MFT model on a newly created 30,000-sentence Chinese aerospace dataset.
Main Results:
- The MFT model demonstrated strong performance in aerospace entity recognition.
- Achieved a notable F1 score of 86.10% on the specialized aerospace dataset.
- The fusion of multi-modal features significantly contributed to the model's effectiveness.
Conclusions:
- The MFT model represents a significant advancement in aerospace domain NER.
- The developed dataset and model provide valuable resources for AI applications in aerospace.
- The findings highlight the potential of advanced NLP techniques in analyzing complex technical data.
