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.
Microsoft.Recognizers.Text.Sequence provides robust recognition and resolution of series entities like phone numbers, URLs, and e-mail and IP addresses.
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...
More information
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...
More information
Robust On-Device or On-Premises Bot development framework with unique bundled architectures. The framework contains OSCOVA and an SIML interpreter. This is a platform agnostic framework and can target multiple platforms delivering similar development experience across platforms. Using the library...
More information
Find the english language indeterminate article ('a' or 'an') for a word. Based on real usage patterns extracted from the wikipedia text dump; can therefore even deal with tricky edge cases such as acronyms (FIAT vs. FAA, NASA vs. NSA) and odd symbols. (Requires .NET Core 1.0 or .NET 4.5)
This package contains the default English models for Catalyst. 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...
More information
This package contains the default Chinese models for Catalyst. 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...
More information
This package contains the default Danish models for Catalyst. 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...
More information
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...
More information