Package edu.stanford.nlp.international.arabic.process

Class Summary
ArabicDocumentReaderAndWriter Reads newline delimited UTF-8 Arabic sentences with or without gold segmentation markers.
ArabicSegmenter Arabic word segmentation model based on conditional random fields (CRF).
ArabicSegmenterFeatureFactory<IN extends CoreLabel> Feature factory for an IOB clitic segmentation model.
ArabicTokenizer<T extends HasWord> Tokenizer for UTF-8 Arabic.
ArabicTokenizer.ArabicTokenizerFactory<T extends HasWord>  
IOBUtils A class for converting strings to input suitable for processing by and IOB sequence model.
 



Stanford NLP Group