Question Answering based Clinical Text Structuring Using Pre-trained Language Model
Jiahui Qiu, Yangming Zhou, Zhiyuan Ma et al. · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · 2019
Clinical text structuring is a critical and fundamental task for clinical research. Traditional methods such as task-specific end-to-end models and pipeline models usually suffer from the lack of dataset and error propagation. In this paper, we present a question answering based clinical text structuring (QA-CTS) task to unify different specific CTS tasks and make dataset shareable. A novel model that aims to introduce domain-specific features (e.g., clinical named entity information) into pre-trained language model is also proposed for QA-CTS task. Experimental results on Chinese pathology reports collected from Ruijing Hospital demonstrate our presented QA-CTS task is very effective to improve the performance on specific tasks. Our proposed model also competes favorably with strong baseline models in specific tasks.
Cited by 3 works. doi:10.1109/bibm47256.2019.8983142 Open-access PDF
Authors
References
- AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Deep Contextualized Word Representations
- TensorFlow: A system for large-scale machine learning
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Image Style Transfer Using Convolutional Neural Networks
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Bilinear CNN Models for Fine-Grained Visual Recognition
- Toward information extraction: identifying protein names from biological papers.
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension