Improving Classification of Infrequent Cognitive Distortions: Domain-Specific Model vs. Data Augmentation.
Xiruo DingKevin LybargerJustin TauscherTrevor CohenPublished in: NAACL-HLT (Student Research Workshop) (2022)
Keyphrases
- data sets
- input data
- domain specific
- computational model
- knowledge discovery
- experimental data
- database
- simulation data
- test data
- prior knowledge
- classification algorithm
- data collection
- pattern recognition
- probabilistic model
- probability distribution
- data structure
- training data
- general purpose
- bayesian methods
- measured data
- support vector machine svm
- image data
- data sources
- data analysis
- feature extraction
- text classification
- data quality
- similarity measure
- high level
- models built