This gem is intended to contain tools for Arabic Natural Language Processing.

Data loaders and abstractions for text and NLP

Tools for processing polish language. Tokenization, scanning, categorization...

Ruby client for Poliqarp (NLP corpus server)

JRuby tools wrapper for Apache OpenNLP

A Lita handler for a question answering (QA) system. Allows you to use CRUD operations and simple NLP. More functionality is coming soon...

Ruby client for Poliqarp (NLP corpus server)

A simple multilingual tokenizer for NLP tasks. This tool provides a CLI and a library for linguistic tokenization which is an anavoidable step for many HLT (human language technology) tasks in the preprocessing phase for further syntactic, semantic and other higher level processing goals. Use it ...

Built-in NLP for Xip Kit via Microsoft's Language Understanding (LUIS).

Implementation of the Rapid Automatic Spanish Keyword Extraction (RASKE) algorithm

Simple Library for NLP over bodies of text

Ruby implementation of a sliding window algorithm, which is useful for NLP applications where scanning text in fixed-sized windows which shrink smaller when no matches are made is useful.

This Ruby gem leverages Machine Learning(ML) techniques to make predictions(forecasts) and classifications in various applications. It provides capabilities such as predicting next month's billing, forecasting upcoming sales orders, identifying patient's potential findings(like Diabetes), determi...

Built-in NLP for Stealth bots via AWS Comprehend.

This is a gem for making it easy to call zemberek2 2.1.1 NLP library functions from JRuby.

Polaris provides methods for polarity analysis (semantic orientations).

Default corpus for Ruby client for Poliqarp (NLP corpus server)

tcf2nif converts NLP data from the TCF format (used by WebLicht) to the RDF-based NIF format.

vaextractor uses rule-based NLP strategy to extract Snellen visual acuities from unstructured ophthalmology clinical notes.

A simple multilingual tokenizer for NLP tasks. This tool provides a CLI and a library for linguistic tokenization which is an anavoidable step for many HLT (human language technology) tasks in the preprocessing phase for further syntactic, semantic and other higher level processing goals. Use it ...