NLP / NaturalLanguage：iOSにおけるテキスト処理フレームワークの解説

import NaturalLanguage

let text = "NaturalLanguage processes text on-device. It supports 30+ languages!"
let tokenizer = NLTokenizer(unit: .word)
tokenizer.string = text

tokenizer.enumerateTokens(in: text.startIndex..<text.endIndex) { range, _ in
    print(text[range])
    return true
}

let sentenceTokenizer = NLTokenizer(unit: .sentence)
sentenceTokenizer.string = text

sentenceTokenizer.enumerateTokens(in: text.startIndex..<text.endIndex) { range, _ in
    print("Sentence: \\(text[range])")
    return true
}

import NaturalLanguage

let recognizer = NLLanguageRecognizer()
recognizer.processString("Hello, how are you? I am learning NaturalLanguage.")

if let language = recognizer.dominantLanguage {
    print("Dominant language: \\(language.rawValue)") // "ru"
}

let hypotheses = recognizer.languageHypotheses(withMaximum: 3)
for (lang, prob) in hypotheses {
    print("\\(lang.rawValue): \\(prob)")
}

import NaturalLanguage

let tagger = NLTagger(tagSchemes: [.lemma, .lexicalClass])
tagger.string = "The cats were running quickly."

tagger.enumerateTags(in: tagger.string!.startIndex..<tagger.string!.endIndex,
    unit: .word,
    scheme: .lexicalClass) { tag, range in
    print("\\(tagger.string![range]): \\(tag?.rawValue ?? "unknown")"
}

let nerTagger = NLTagger(tagSchemes: [.nameType])
nerTagger.string = "Tim Cook announced Apple's new headquarters in Cupertino."

nerTagger.enumerateTags(in: nerTagger.string!.startIndex..<nerTagger.string!.endIndex,
    unit: .word,
    scheme: .nameType) { tag, range in
    if tag != nil {
        print("\\(nerTagger.string![range]): \\(tag!.rawValue)"
    }
}

import NaturalLanguage

let sentimentPredictor = try NLModel(mlModel: SentimentModel().model)
let sentiment = sentimentPredictor.predictedLabel(for: "This app is amazing!")
print("Sentiment: \\(sentiment ?? "neutral")") // "positive"