Related Experiment Video
Updated: Dec 7, 2025
05:56
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
3.0K
Chinese medical named entity recognition based on multi-granularity semantic dictionary and multimodal tree
Caiyu Wang1, Hong Wang2, Hui Zhuang1
1School of Information Science and Engineering, Shandong Normal University, Jinan 250358, China.
Journal of Biomedical Informatics
|October 3, 2020
Summary
This study introduces an advanced Chinese named entity recognition (NER) method using a multi-granularity semantic dictionary and multimodal trees. The novel approach significantly improves knowledge extraction from complex clinical texts.
Area of Science:
- Natural Language Processing
- Clinical Informatics
- Artificial Intelligence
Background:
- Named Entity Recognition (NER) is crucial for extracting knowledge from clinical texts.
- Existing Chinese NER methods face challenges like text complexity, segmentation errors, and incomplete semantic extraction.
Purpose of the Study:
- To develop a novel Chinese NER method to address limitations in clinical text analysis.
- To enhance the accuracy and completeness of knowledge extraction in the medical domain.
Main Methods:
- Proposed a Chinese NER method integrating a multi-granularity semantic dictionary and multimodal trees.
- Utilized multimodal trees for extracting diverse semantic words.
- Incorporated boundary information extraction and multi-granularity feature fusion.
Main Results:
- The proposed model demonstrated superior performance compared to current state-of-the-art methods.
- Experimental verification confirmed the effectiveness of the new approach.
Conclusions:
- The developed Chinese NER method effectively overcomes existing challenges in clinical text analysis.
- This approach offers a significant advancement for knowledge mining in the medical field.
