Structured prediction models for RNN based sequence labeling in clinical text
By Abhyuday N. Jagannatha, Hong Yu. 2016
210 citations recorded by the source corpus.
Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities such as medication, indication, and side-effects from Electronic Health Record narratives. Sequence labeling in this domain, presents its own set of challenges and objectives. In this work we experimented with various CRF based structured learning models with Recurrent Neural Networks. We extend the previously studied LSTM-CRF models with explicit modeling of pairwise potentials. We also propose an approximate version of skip-chain CRF inference with RNN potentials. We use these methodologies1 for structured prediction in order to improve the exact phrase detection of various medical entities.
Subfields: Artificial Intelligence, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yuan Luo
- Zexian Zeng
- Sebastian Gehrmann
- Tristan Naumann
- Xiaoyu Li
- Yu Deng
- Franck Dernoncourt
- Steven Layne
In Molecular Biology
- Zexian Zeng
- Tristan Naumann
- Xiaoyu Li
- Yu Deng
- Yuan Luo
- Parisa Rashidi
- Medhat A. Moussa
- Franck Dernoncourt
Citations in the corpus
- Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “[161], [162] experimented with recurrent neural networks (RNNs), long shortterm memory (LSTM), gated recurrent units (GRUs), bidirectional LSTMs, combinations of LSTMs with CRF, and CRF to”
- Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends (2020, methodology): “CRFs are commonly used in NLP problems such as modeling word-tags [41], [42], or in the image domain for semantic segmentation [117].”
- Text feature extraction based on deep learning: a review (2017, background): “Reference [110] extends the previously studied CRFLSTM (conditional random field, long short-term mem-”
- Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (2017, background): “[16], [17] treat the concept extraction problem as a sequence labeling task whose goal is to assign one of nine clinically relevant tags to each word in a clinical note.”
- Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation (2019, methodology): “Alternative approaches for similar tasks are CRFs that estimate pairwise potentials rather than using a fixed transition matrix (Jagannatha and Yu, 2016) or high-order CRFs which outperform SCRFs in some sequence labeling tasks (Cuong et al.”