We Need to Talk About Classification Evaluation Metrics in NLP.
Peter VickersLoïc BarraultEmilio MontiNikolaos AletrasPublished in: CoRR (2024)
Keyphrases
- learning to rank
- evaluation metrics
- supervised learning
- average precision
- document retrieval
- evaluation framework
- classification accuracy
- natural language processing
- evaluation methodology
- evaluation methods
- feature selection
- text classification
- feature extraction
- decision trees
- machine learning
- text mining
- information extraction
- structured data
- training set
- benchmark datasets
- question answering
- active learning
- pairwise
- digital libraries