apertium-html-toolsWeb application providing a fully localised interface for text/website/document translation, analysis and generation powered by Apertium.
react-taggyA simple zero-dependency React component for tagging user-defined entities within a block of text.
ritaWebsite, documentation and examples for RiTa
fillersList of (possible) English filler words
gdpr-fingerprint-piiUse Watson Natural Language Understanding and Watson Knowledge Studio to fingerprint personal data from unstructured documents
nl4dvA python toolkit to create Visualizations (Vis) using natural language (NL) or add an NL interface to existing Vis.
openvalidationCompose validation rules in the language you use every day, openVALIDATION handles code creation for you.
remark-retextplugin to transform from remark (Markdown) to retext (natural language)
n2wordsConvert numerical numbers to written numbers, in 25+ languages.
buzzwordsList of (possible) English buzzword words
hedgesList of (possible) English hedge words
TextFeatureSelectionPython library for feature selection for text features. It has filter method, genetic algorithm and TextFeatureSelectionEnsemble for improving text classification models. Helps improve your machine learning models
nalcosSearch Git commits in natural language
parallel-corpora-toolsTools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.
watson-document-classifierAugment IBM Watson Natural Language Understanding APIs with a configurable mechanism for text classification, uses Watson Studio.
LangageLinotteCode source officiel du langage de programmation Linotte - Langage de programmation en français simple créé dans le but de permettre aux enfants et aux personnes n'ayant pas une connaissance approfondie de l’informatique d’apprendre la programmation facilement.
weaselsList of (possible) English weasel words
fountainNatural Language Data Augmentation Tool for Conversational Systems
linguistic-datasets-portugueseLinguistic Datasets for Portuguese: Lista de conjuntos de dados linguísticos para língua portuguesa com licença flexíveis: banco de dados, lista de palavras, sinônimos, antônimos, dicionário temático, tesauro, linked data, semântica, ontologia e representação de conhecimento
watson-multimedia-analyzerWARNING: This repository is no longer maintained ⚠️ This repository will not be updated. The repository will be kept available in read-only mode. A Node app that use Watson Visual Recognition, Speech to Text, Natural Language Understanding, and Tone Analyzer to enrich media files.
LibN3LLibN3L: A light-weight neural network package for natural language