Use of Conventional Machine Learning to Optimize Deep Learning Hyper-parameters for NLP Labeling Tasks

Simple item page
dc.contributor.authorGu, Yang
dc.contributor.authorLeroy, Gondy
dc.date.accessioned2020-01-04T07:21:20Z
dc.date.available2020-01-04T07:21:20Z
dc.date.issued2020-01-07
dc.description.abstractDeep learning delivers good performance in classification tasks, but is suboptimal with small and unbalanced datasets, which are common in many domains. To address this limitation, we use conventional machine learning, i.e., support vector machines (SVM) to tune deep learning hyper-parameters. We evaluated our approach using mental health electronic health records in which diagnostic criteria needed to extracted. A bidirectional Long Short-Term Memory network (BI-LSTM) could not learn the labels for the seven scarcest classes, but saw an increase in performance after training with optimal weights learned from tuning SVMs. With these customized class weights, the F1 scores for rare classes rose from 0 to values ranging from 18% to 57%. Overall, the BI-LSTM with SVM customized class weights achieved a micro-average of 47.1% for F1 across all classes, an improvement over the regular BI-LSTM’s 45.9%. The main contribution lies in avoiding null performance for rare classes.
dc.format.extent10 pages
dc.identifier.doi10.24251/HICSS.2020.128
dc.identifier.isbn978-0-9981331-3-3
dc.identifier.urihttp://hdl.handle.net/10125/63867
dc.language.isoeng
dc.relation.ispartofProceedings of the 53rd Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectData, Text, and Web Mining for Business Analytics
dc.subjectdeep learning
dc.subjectdesign science
dc.subjectmachine learning
dc.subjectnatural language processing
dc.titleUse of Conventional Machine Learning to Optimize Deep Learning Hyper-parameters for NLP Labeling Tasks
dc.typeConference Paper
dc.type.dcmiText

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0102.pdf
Size:
716.38 KB
Format:
Adobe Portable Document Format
Download

Collections

Data, Text, and Web Mining for Business Analytics