High Recall, Small Data: The Challenges of Within-System Evaluation in a Live Legal Search System.
Gineke WiggersSuzan VerberneArjen P. de VriesRoel van der BurgPublished in: CoRR (2024)
Keyphrases
- data sets
- original data
- database
- raw data
- data analysis
- high recall
- image data
- data sources
- search algorithm
- prior knowledge
- data structure
- high quality
- small number
- training data
- learning algorithm
- data processing
- data collection
- computer systems
- statistical analysis
- exact match
- data quality
- lessons learned
- data distribution
- experimental data
- missing data
- cloud computing
- input data
- data mining techniques
- knowledge discovery
- data mining