What question did this study set out to answer?

The research aims to enhance medical named entity recognition using a novel Lattice-based Transfer Learning framework.

Medical Named Entity Recognition via Lattice-Enhanced Transfer Learning with Random Attention

View Full Paper

Ask AI

Bookmark

Authors

Novel framework improves medical named entity recognition, enhancing accuracy in low-resource conditions.

The research aims to enhance medical named entity recognition using a novel Lattice-based Transfer Learning framework.
Developed a Lattice-based Transfer Learning framework for Chinese medical NER.
Integrated Inter-Attention and Random Attention to improve semantic representation.
Balanced character- and word-level features in the model design.
Implemented a conditional random field layer for sequence labeling.
Achieved F1 scores of 90.55%, 80.72%, and 83.71% on TCM-Methods, Tianchi2020, and CCKS2019 datasets respectively.
Demonstrated improved robustness and reduced source-domain bias through Random Attention.

Xu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark