Abstract

The complexity of syntax and the specialized nature of Chinese electronic medical record data make it challenging to accurately identify medical entities using named entity recognition models. In order to precisely extract complex medical vocabulary from electronic medical records, this paper proposes a multi-feature-based named entity recognition model that addresses the issue of insufficient internal feature extraction in the FLAT model. Firstly, the radical and pinyin features of Chinese characters are extracted for enrichment and perfection of their semantic information. These features are then combined with the word embeddings extracted by the FLAT-lattice method. Finally, the fused features and position encoding are input to the Transformer encoder for encoding, followed by decoding using the CRF method. Experimental results demonstrate that the proposed model outperforms many existing algorithms on the CCL2021 dataset, with an F1 score of up to 91.75%.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.