OBJECTIVE: Abbreviations sense disambiguation is a special case of word sense disambiguation. Machine learning methods based on neural networks showed promising results for word sense disambiguation (Festag and Spreckelsen, 2017) [1] and, here we assess their effectiveness for abbreviation sense disambiguation. METHODS: Convolutional Neural Network (CNN) models were trained, one for each abbreviation, to disambiguate abbreviation senses. A reverse substitution (of long forms with short forms) method from a previous study was used on clinical narratives from Cleveland Clinic, USA, to auto-generate training data. Accuracy of the CNN and traditional Support Vector Machine (SVM) models were studied using: (a) 5-fold cross validation on the auto-generated training data; (b) a manually created, set-aside gold standard; and (c) 10-fold cross validation on a publicly available dataset from a previous study. RESULTS: CNN improved accuracy by 1-4 percentage points on all the three datasets compared to SVM, and the improvement was the most for the set-aside dataset. The improvement was statistically significant at p < 0.05 on the auto-generated dataset. We found that for some common abbreviations, sense distributions mismatch between the test and auto generated training data, and mitigating the mismatch significantly improved the model accuracy. CONCLUSION: The neural network models work well in disambiguating abbreviations in clinical narratives, and they are robust across datasets. This avoids feature-engineering for each dataset. Coupled with an enhanced auto-training data generation, neural networks can simplify development of a practical abbreviation disambiguation system.
OBJECTIVE: Abbreviations sense disambiguation is a special case of word sense disambiguation. Machine learning methods based on neural networks showed promising results for word sense disambiguation (Festag and Spreckelsen, 2017) [1] and, here we assess their effectiveness for abbreviation sense disambiguation. METHODS: Convolutional Neural Network (CNN) models were trained, one for each abbreviation, to disambiguate abbreviation senses. A reverse substitution (of long forms with short forms) method from a previous study was used on clinical narratives from Cleveland Clinic, USA, to auto-generate training data. Accuracy of the CNN and traditional Support Vector Machine (SVM) models were studied using: (a) 5-fold cross validation on the auto-generated training data; (b) a manually created, set-aside gold standard; and (c) 10-fold cross validation on a publicly available dataset from a previous study. RESULTS: CNN improved accuracy by 1-4 percentage points on all the three datasets compared to SVM, and the improvement was the most for the set-aside dataset. The improvement was statistically significant at p < 0.05 on the auto-generated dataset. We found that for some common abbreviations, sense distributions mismatch between the test and auto generated training data, and mitigating the mismatch significantly improved the model accuracy. CONCLUSION: The neural network models work well in disambiguating abbreviations in clinical narratives, and they are robust across datasets. This avoids feature-engineering for each dataset. Coupled with an enhanced auto-training data generation, neural networks can simplify development of a practical abbreviation disambiguation system.
Authors: Jinhe Shi; Xiangyu Gao; William C Kinsman; Chenyu Ha; Guodong Gordon Gao; Yi Chen Journal: Artif Intell Med Date: 2021-12-02 Impact factor: 5.326
Authors: Denis Newman-Griffis; Guy Divita; Bart Desmet; Ayah Zirikly; Carolyn P Rosé; Eric Fosler-Lussier Journal: J Am Med Inform Assoc Date: 2021-03-01 Impact factor: 4.497