Label-aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition
This addresses the challenge of training universal medical NER systems due to specialty differences and high annotation costs, with potential adaptation to non-medical NER tasks.
The paper tackles the problem of named entity recognition (NER) across different medical specialties, where terminologies and writing styles vary, by proposing a label-aware double transfer learning framework (La-DTL) to enable a system designed for one specialty to be applied to another with minimal annotation, achieving consistent accuracy improvements in experiments on 12 cross-specialty NER tasks.
We study the problem of named entity recognition (NER) from electronic medical records, which is one of the most fundamental and critical problems for medical text mining. Medical records which are written by clinicians from different specialties usually contain quite different terminologies and writing styles. The difference of specialties and the cost of human annotation makes it particularly difficult to train a universal medical NER system. In this paper, we propose a label-aware double transfer learning framework (La-DTL) for cross-specialty NER, so that a medical NER system designed for one specialty could be conveniently applied to another one with minimal annotation efforts. The transferability is guaranteed by two components: (i) we propose label-aware MMD for feature representation transfer, and (ii) we perform parameter transfer with a theoretical upper bound which is also label aware. We conduct extensive experiments on 12 cross-specialty NER tasks. The experimental results demonstrate that La-DTL provides consistent accuracy improvement over strong baselines. Besides, the promising experimental results on non-medical NER scenarios indicate that La-DTL is potential to be seamlessly adapted to a wide range of NER tasks.