Created
November 21, 2017 16:58
-
-
Save agermanidis/8e28e6864f39f85d4e6db4ca43ddebac to your computer and use it in GitHub Desktop.
Named Entity Extraction - Swift
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
func getEntities (_ sentence : String) -> [String] { | |
let tagger = NSLinguisticTagger(tagSchemes: [.nameType], options: 0) | |
let options: NSLinguisticTagger.Options = [.omitPunctuation, .omitWhitespace] | |
tagger.string = sentence | |
let range = NSRange(location:0, length: sentence.utf16.count) | |
var prevTag : NSLinguisticTag? = nil | |
var accName : String = "" | |
let selectedTags : [NSLinguisticTag] = [.personalName, .organizationName, .placeName] | |
var entities : [String] = [] | |
tagger.enumerateTags(in: range, unit: .word, scheme: .nameType, options: options) { tag, tokenRange, stop in | |
if let tag = tag { | |
let name = (sentence as NSString).substring(with: tokenRange) | |
if let prevTag = prevTag, prevTag == tag { | |
accName += " " + name | |
} else { | |
if prevTag != nil && selectedTags.contains(prevTag!) { | |
entities.append(accName) | |
} | |
accName = name | |
} | |
prevTag = tag | |
} | |
} | |
if prevTag != nil && selectedTags.contains(prevTag!) { | |
entities.append(accName) | |
} | |
return entities | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment