ANETAC: Arabic Named Entity Transliteration and Classification Dataset.
Mohamed Seghir Hadj AmeurFarid MezianeAhmed GuessoumPublished in: CoRR (2019)
Keyphrases
- named entities
- unsupervised learning
- question answering
- named entity recognition
- text mining
- natural language processing
- information extraction
- relation extraction
- named entity extraction
- co occurrence
- image classification
- classification accuracy
- machine learning
- text classification
- pattern recognition
- annotated corpus
- decision trees
- maximum entropy model
- feature extraction
- information retrieval
- machine translation
- model selection
- maximum likelihood
- feature space
- data sets
- training set
- supervised learning
- class labels
- feature selection
- linguistic features
- expert systems