A New Dataset for Topic-Based Paragraph Classification in Genocide-Related Court Transcripts.
Miriam SchirmerUdo KruschwitzGregor DonabauerPublished in: LREC (2022)
Keyphrases
- classification accuracy
- uci datasets
- pattern recognition
- machine learning
- classification models
- feature set
- classification algorithm
- benchmark datasets
- decision trees
- training dataset
- feature space
- feature selection
- automatic classification
- pattern classification
- machine learning algorithms
- image classification
- classification systems
- support vector
- svm classifier
- classification scheme
- classification method
- machine learning methods
- training samples
- supervised learning
- support vector machine
- document classification
- classification rules
- feature extraction
- news stories
- preprocessing
- content analysis
- decision rules
- class labels
- topic models
- model selection
- query expansion