NaturalLanguage + Translation

Analyze natural language text for tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, language identification, and word/sentence embeddings. Translate text between languages with the Translation framework. Targets Swift 6.3 / iOS 26+.

This skill covers two related frameworks: NaturalLanguage (NLTokenizer, NLTagger, NLEmbedding) for on-device text analysis, and Translation (TranslationSession, LanguageAvailability) for language translation.

Contents

• Setup
• Tokenization
• Language Identification
• Part-of-Speech Tagging
• Named Entity Recognition
• Sentiment Analysis
• Text Embeddings
• Translation
• Common Mistakes
• Review Checklist
• References

Setup

Import NaturalLanguage for text analysis and Translation for language translation. No special entitlements or capabilities are required for NaturalLanguage. Translation requires iOS 17.4+ / macOS 14.4+.

import NaturalLanguage
import Translation

NaturalLanguage classes (NLTokenizer, NLTagger) are not thread-safe. Use each instance from one thread or dispatch queue at a time.

Tokenization

Segment text into words, sentences, or paragraphs with NLTokenizer.

import NaturalLanguage

func tokenizeWords(in text: String) -> [String] {
    let tokenizer = NLTokenizer(unit: .word)
    tokenizer.string = text

    let range = text.startIndex..<text.endIndex
    return tokenizer.tokens(for: range).map { String(text[$0]) }
}

Token Units

Enumerating with Attributes

Use enumerateTokens(in:using:) to detect numeric or emoji tokens.

let tokenizer = NLTokenizer(unit: .word)
tokenizer.string = text

tokenizer.enumerateTokens(in: text.startIndex..<text.endIndex) { range, attributes in
    if attributes.contains(.numeric) {
        print("Number: \(text[range])")
    }
    return true // continue enumeration
}

Language Identification

Detect the dominant language of a string with NLLanguageRecognizer.

func detectLanguage(for text: String) -> NLLanguage? {
    NLLanguageRecognizer.dominantLanguage(for: text)
}

// Multiple hypotheses with confidence scores
func languageHypotheses(for text: String, max: Int = 5) -> [NLLanguage: Double] {
    let recognizer = NLLanguageRecognizer()
    recognizer.processString(text)
    return recognizer.languageHypotheses(withMaximum: max)
}

Constrain the recognizer to expected languages for better accuracy on short text.

let recognizer = NLLanguageRecognizer()
recognizer.languageConstraints = [.english, .french, .spanish]
recognizer.processString(text)
let detected = recognizer.dominantLanguage

Part-of-Speech Tagging

Identify nouns, verbs, adjectives, and other lexical classes with NLTagger.

func tagPartsOfSpeech(in text: String) -> [(String, NLTag)] {
    let tagger = NLTagger(tagSchemes: [.lexicalClass])
    tagger.string = text

    var results: [(String, NLTag)] = []
    let range = text.startIndex..<text.endIndex
    let options: NLTagger.Options = [.omitPunctuation, .omitWhitespace]

    tagger.enumerateTags(in: range, unit: .word, scheme: .lexicalClass, options: options) { tag, tokenRange in
        if let tag {
            results.append((String(text[tokenRange]), tag))
        }
        return true
    }
    return results
}

Common Tag Schemes

Named Entity Recognition

Extract people, places, and organizations.

func extractEntities(from text: String) -> [(String, NLTag)] {
    let tagger = NLTagger(tagSchemes: [.nameType])
    tagger.string = text

    var entities: [(String, NLTag)] = []
    let options: NLTagger.Options = [.omitPunctuation, .omitWhitespace, .joinNames]

    tagger.enumerateTags(
        in: text.startIndex..<text.endIndex,
        unit: .word,
        scheme: .nameType,
        options: options
    ) { tag, tokenRange in
        if let tag, tag != .other {
            entities.append((String(text[tokenRange]), tag))
        }
        return true
    }
    return entities
}
// NLTag values: .personalName, .placeName, .organizationName

Sentiment Analysis

Score text sentiment from -1.0 (negative) to +1.0 (positive).

func sentimentScore(for text: String) -> Double? {
    let tagger = NLTagger(tagSchemes: [.sentimentScore])
    tagger.string 
how to use natural-language
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use natural-language on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add natural-language
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/dpearson2699/swift-ios-skills --skill natural-languagecopy
The skills CLI fetches natural-language from GitHub repository dpearson2699/swift-ios-skills and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/natural-language
Reload or restart Cursor to activate natural-language. Access the skill through slash commands (e.g., /natural-language) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?