Latent Feature-based Data Splits to Improve Generalisation Evaluation: A Hate Speech Detection Case Study.
Maike ZüfleVerna DankersIvan TitovPublished in: CoRR (2023)
Keyphrases
- data sets
- case study
- statistical analysis
- high quality
- knowledge discovery
- data collection
- data sources
- database
- small number
- raw data
- missing data
- data structure
- data processing
- training data
- computer systems
- input data
- data quality
- statistical methods
- experimental data
- detection method
- information retrieval
- object detection
- data points
- wireless sensor networks
- hidden markov models
- prior knowledge
- relational databases
- high dimensional