Manual Corpus Annotation: Giving Meaning to the Evaluation Metrics.
Yann MathetAntoine WidlöcherKarën FortClaire FrançoisOlivier GalibertCyril GrouinJuliette KahnSophie RossetPierre ZweigenbaumPublished in: COLING (Posters) (2012)
Keyphrases
- evaluation metrics
- manual annotation
- manually annotated
- annotated corpus
- precision and recall
- labor intensive
- average precision
- semi automatic
- relation extraction
- automatic annotation
- learning to rank
- evaluation framework
- hand crafted
- metadata
- evaluation measures
- natural language
- image annotation
- error prone
- semantic annotation
- test set
- digital libraries
- named entity recognition
- named entities
- multimedia
- active learning
- image retrieval
- statistical machine translation
- data sets