[NEW] SAFAR V2 has been released.
[NEW] This project is open to your contributions. Everyone can contribute in its development.
SAFAR is a platform dedicated to ANLP (Arabic Natural Language Processing). It is open source, cross-platform, modular, and provides an integrated development environment (IDE). It includes :
» Resources needed for different treatments ANLP
» Basic levels modules of language, especially those of the Arabic language, namely morphology, syntax and semantics
» Applications for the ANLP
General architecture of SAFAR
Each layer is developed as a set of reusable Java API:
» Tools: includes a range of technical services (statistical functions, test tools, tokenization, sentences splitting etc.)
» Resource Services: Provides resources language consultation such as lexicons and corpora.
» NLP services: Contains three layers of processing language Regular (morphology, syntax and semantics)
» Applications: Contains high-level applications that use layers listed above.
» Client: In case the user needs to directly use services layer.
SAFAR V2 features
The services currently provided by SAFAR V2 and which are ready to be used are:
Morpho-Syntactic Processor [NEW]
Syntactic parsers :
Stanford Parser [NEW]
Morphological analyzers :
Alkhalil Morphological Analyzer
BAMA Morphological Analayzer
MADAMIRA Morphological Analayzer [NEW]
ISRI stemmer [NEW]
Tashaphyne stemmer [NEW]
Motaz stemmer [NEW]
Benchmark (to evaluate morphological analyzers)
Particles lexicon [NEW]
Al wassit dictionary [NEW]
Contemporary dictionary [NEW]
Ontology (AWN and extended AWN) [NEW]
Excel and csv outputs in SAFAR web [NEW]