Natural Language

Overview

The Natural Language framework provides a variety of natural language processing (NLP) functionality with support for many different languages and scripts. Use this framework to segment natural language text into paragraphs, sentences, or words, and tag information about those segments, such as lexical class, lemma, script, and language.

[Image]

Use this framework to perform tasks like:

• Language identification, automatically detecting the language of a piece of text.

• Tokenization, breaking up a piece of text into linguistic units or tokens.

• Parts-of-speech tagging, marking up individual words with their part of speech.

• Lemmatization, deducing a word’s stem based on its morphological analysis.

• Named entity recognition, identifying tokens as names of people, places, or organizations.

• Sentiment classification, scoring text on a scale from negative to positive.

• Text embedding, mapping words and sentences to vectors so you can measure the similarity between pieces of text, using either word and sentence embeddings or transformer-based contextual embeddings.

You can also use this framework with Create ML to train and deploy custom natural language models. For more information, see Creating a text classifier model and Creating a word tagger model.

Topics

Tokenization

• Tokenizing natural language text
• NLTokenizer

Language identification

• Identifying the language in text
• NLLanguageRecognizer
• NLLanguage

Linguistic tags

• Identifying parts of speech
• Identifying people, places, and organizations
• NLTagger

Text embedding

• Finding similarities between pieces of text
• NLEmbedding

Contextual embedding

• NLContextualEmbedding
• NLContextualEmbeddingKey
• NLScript

Natural language models

• Creating a text classifier model
• Creating a word tagger model
• NLModel