Events

What is Nooj ?

Smart

Sophisticated linguistic engine

Versatile

More than 20 languages are known by the software

Cross-Platform

More than 150 file formats on windows, Mac and Linux.

Flexible

Made for developement an fully customizable

Presentation

NooJ is a linguistic development environment software developed by Max Silberztein. Using mathematical rules it provides linguistic tools to help customers formalize natural languages and aid in the building of software able to automatically process texts written in natural language (Natural Language Processing, or NLP).

This application of descriptive linguistics includes spell-checkers, intelligent search engines, information extractors and annotators, automatic summary producers, automatic translators, and more.


Analysis of the televised debate between Macron and Marine le Pen on May 3, 2017

Arabic

Tutorials and Linguistic Ressources


Arabic module

Mesfar Slim, Université de Franche-Comté The Arabic module includes: -- one full dictionary named EL-DICAR (ELectronic DICtionary for ARabic):
One full dictionary named EL-DICAR (ELectronic DICtionary for ARabic) including more than 52000 lexical entries:
1/ 19504 nouns (N)
2/ 10375 verbs (V)
3/ 5816 adjectives (ADJ)
4/ 1236 particles (PREP, ADV, REL, DEM)
5/ 3686 loclizations (N+LOC)
6/ 11860 First names (N+Prenom)

-- one sample dictionary (_Example.dic) with its corresponding inflectional grammar(_Example.nof)
-- a file _properties.def that includes a listing of the dictionary codes, inflections, morphology and derivations
-- three morphological grammars:
1/ REQUIRED : Graph_Morpho.nom : a tokenization grammar to identify and annotate morphemes in agglutinated forms (this grammar has to be checked in Info > Preferences)
2/ OPTIONAL : Graph_Morpho_AlifToHamza.nom : a spelling correction grammar that converts Alif to Hamza (if used, this grammar should be associated with a low level priority)
3/ OPTIONAL : Graph_Morpho_HamzaToAlif.nom : a spelling correction grammar that converts Hamza to Alif (if used, this grammar has to be associated with a low level priority)
-- one syntactic grammar: Graph_Timex.nog : a local grammar to recognize temporal expressions (date, hour, age, period, ...)
-- two texts :
1/ declaration_rights.not : The Universal Declaration of the Rights of Man and of the Citizen
2/ example.not : a collection of samples from newspapers that include temporal expressions


Tutorial 1: Introduction

An introduction video for NooJ in Arabic:

Tutorial 2: NooJ dictionaries

NooJ dictionaries

Tutorial 3: Contrat and Debugs

Contrat and Debugs

Tutorial 4: Morphological grammars

Morphological grammars

Tutorial 5: Text and Corpus

MText and Corpus

Tutorial 6: Export annotated text as an XML document

Export annotated text as an XML documents

Tutorial 7: Regular Expression

Regular Expression

Tutorial 8: Syntactic grammars

Syntactic grammars

Tutorial 9: Statistical analyses

Statistical analyses

Tutorial 10: Concordance

Concordance

Inscription à : Articles (Atom)