Microsoft.ML.Tokenizers contains the implmentation of the tokenization used in the NLP transforms.
Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, and mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. Stanford CoreNLP is an integrated framework, which make it very easy to apply a bunch of language analysis tools to a piece of text. Starting from plain text, you can run all the tools on it with just two lines of code. Its analyses provide the foundational building blocks for higher-level and domain-specific text understanding applications.
Microsoft.Recognizers.Text provides base classes for robust recognition and resolution of text entities.
Microsoft.Recognizers.Text.DataTypes.TimexExpression provides parsing and evaluation of TIMEX expressions.
Microsoft.Recognizers.Text.Number provides robust recognition and resolution of numbers expressed in English, Spanish, French, Portuguese, Chinese, German, Dutch, Japanese, Italian, Turkish, Swedish, and Hindi.
Microsoft.Recognizers.Text.NumberWithUnit provides robust recognition and resolution of numbers with units expressed in English, Spanish, French, Portuguese, Chinese, German, Dutch, Italian, Turkish, and Hindi.
Microsoft.Recognizers.Text.DateTime provides robust recognition and resolution of Date and Time expressed in English, Spanish, French, Portuguese, Chinese, German, Italian, and Turkish.
Microsoft.Recognizers.Text.Choice provides recognition of Boolean (yes/no) answers expressed in English, Portuguese, Spanish, Japanese, Chinese, Dutch, French, German, Italian, Swedish, Bulgarian, Turkish, Hindi, and Arabic. As well as base classes to support lists of alternative choices.
C# port of the Java OpenNLP tools retrieved from http://sharpnlp.codeplex.com/ (it's not mine!)
Abodit Natural Language Engine - WordNet Add-on. Portions of this dictionary have been created using WordNet from Princeton University and are subject to the following license agreement. See http://wordnet.princeton.edu/wordnet/license/
The 'DetectiveAI' library provides a robust AI-generated text detection service. It leverages multiple advanced analysis techniques to assess the likelihood of a given text being AI-generated. The service provides a probability score between 0 and 1, with 0 indicating a lower probability and 1 indicating a higher probability of AI authorship.
The Apache OpenNLP library is a machine learning based toolkit for the processing of natural language text. It supports the most common NLP tasks, such as tokenization, sentence segmentation, part-of-speech tagging, named entity extraction, chunking, parsing, and coreference resolution. These tasks are usually required to build more advanced text processing services. OpenNLP also included maximum entropy and perceptron based machine learning.
Catalyst is a Natural Language Processing library built from scratch for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models. You can install language-specific models with the model packages Catalyst.Models.[Language], like: Catalyst.Models.English.
Microsoft.Recognizers.Text.Sequence provides robust recognition and resolution of series entities like phone numbers, URLs, and e-mail and IP addresses.
Stanford NER (also known as CRFClassifier) is a Java implementation of a Named Entity Recognizer. Named Entity Recognition (NER) labels sequences of words in a text which are the names of things, such as person and company names, or gene and protein names. The software provides a general (arbitrary order) implementation of linear chain Conditional Random Field (CRF) sequence models, coupled with well-engineered feature extractors for Named Entity Recognition.
LLamaSharp is a cross-platform library to run 🦙LLaMA/Mtmd model (and others) in your local device. Based on [llama.cpp](https://github.com/ggerganov/llama.cpp), inference with LLamaSharp is efficient on both CPU and GPU. With the higher-level APIs and RAG support, it's convenient to deploy LLM (Large Language Model) in your application with LLamaSharp.
A Part-Of-Speech Tagger (POS Tagger) is a piece of software that reads text in some language and assigns parts of speech to each word (and other token), such as noun, verb, adjective, etc., although generally computational applications use more fine-grained POS tags like 'noun-plural'.
Microsoft.Recognizers.Definitions provides base regex definitions for robust recognition and resolution of text entities.
A natural language parser is a program that works out the grammatical structure of sentences, for instance, which groups of words go together (as \"phrases\") and which words are the subject or object of a verb. Probabilistic parsers use knowledge of language gained from hand-parsed sentences to try to produce the most likely analysis of new sentences.